高级检索+

棉花轧工质量机器视觉检测系统设计与试验

夏彬, 史书伟, 张若宇, 秦建锋, 刘妍妍, 常金强

夏彬, 史书伟, 张若宇, 秦建锋, 刘妍妍, 常金强. 棉花轧工质量机器视觉检测系统设计与试验[J]. 农业机械学报, 2023, 54(11): 189-197.
引用本文: 夏彬, 史书伟, 张若宇, 秦建锋, 刘妍妍, 常金强. 棉花轧工质量机器视觉检测系统设计与试验[J]. 农业机械学报, 2023, 54(11): 189-197.
XIA Bin, SHI Shu-wei, ZHANG Ruo-yu, QIN Jian-feng, LIU Yan-yan, CHANG Jin-qiang. Design and Test of Machine Vision Inspection System for Cotton Preparation[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(11): 189-197.
Citation: XIA Bin, SHI Shu-wei, ZHANG Ruo-yu, QIN Jian-feng, LIU Yan-yan, CHANG Jin-qiang. Design and Test of Machine Vision Inspection System for Cotton Preparation[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(11): 189-197.

棉花轧工质量机器视觉检测系统设计与试验

基金项目: 

国家重点研发计划项目(2022YFD2002404)

兵团科技攻关计划项目(2022DB003)

兵团财政科技计划项目(2023AB014)

详细信息
    作者简介:

    夏彬(1983—),男,高级工程师,主要从事棉花加工智能技术装备研究,E-mail:binxia@126.com

    通讯作者:

    张若宇(1980—),男,教授,博士生导师,主要从事农产品智能检测技术与装备研究,E-mail:ry248@163.com

  • 中图分类号: TS111.9;TP391.41

Design and Test of Machine Vision Inspection System for Cotton Preparation

  • 摘要: 针对棉花轧工质量现行人工感官检验中存在的劳动强度大、主观性强、检测效率低等问题,设计一种基于机器视觉的棉花轧工质量检测系统。系统由压棉机构、图像采集机构、检测处理机、检测控制板卡和触控显示屏组成。设计了低角度直接照明系统与图像采集机构,LED光源以检测视窗法线呈45°方向照射,工业相机透过光学玻璃采集棉花图像。采用图像纹理特征表达棉花外观形态,通过测定轧工质量实物标准的角二阶矩,建立图像纹理特征与外观形态关系模型,融合噪声点评价与高低阈值自适应的Canny方法进行图像滤波与分割识别,根据欧氏距离进行轧工质量等级判定,并选取棉样进行系统试验验证。结果表明,轧工质量实物标准P1、P2、P3的角二阶矩分别为[0.893 2,1]、[0.689 1,0.776 1]、[0.213 6,0.587 3],各等级间的角二阶矩纹理特征值区别明显,验证了图像纹理表达棉花外观形态的可行性。系统的疵点粒数指标检测相对偏差为0.15,疵点与背景的分离效果明显。与国标检验方法相比,轧工质量视觉系统检测准确率达94.20%,检测偏差上下浮动不大于1个轧工质量等级,与国标检验结果一致性高。单个棉样系统检测耗时1.2 s,检测效率提升77.36%。系统能够满足现场使用要求,为棉花轧工质量指标的仪器化检测提供了技术参考。
    Abstract: Aiming at the problems of labor intensity, strong subjectivity and low detection efficiency in the current manual sensory inspection of cotton preparation, a machine vision-based cotton preparation inspection system was designed. The system consisted of cotton pressing mechanism, image acquisition mechanism, detection processor, detection control board and touch screen. Firstly, a low-angle direct lighting system and an image acquisition mechanism were designed, where the LED light source was illuminated at an angle of 45° to the normal of the inspection window, and the industrial camera collected cotton images through the optical glass. Then the system adopted image texture features to express the appearance morphology of cotton, and established a relationship model between image texture features and appearance morphology by measuring the angular second moment of cotton preparation sample standards. In the adaptive filtering and Canny algorithm, it integrated the noise point evaluation and the high and low threshold adaptive methods for image filtering and segmentation identification, and the ginning quality level determination was made according to the Euclidean distance. Finally, cotton samples were selected for system performance test verification. The results showed that the angluar second moment of the ginning quality physical standards P1, P2 and P3 were [0.893 2, 1], [0.689 1, 0.776 1], [0.213 6, 0.587 3], respectively, and the difference in the texture eigenvalues of the angular second moment between the grades was obvious, which verified the feasibility of the image texture to express the appearance and morphology of cotton. The relative deviation of the inspection of the number of defects index of the system was 0.15, and the separation effect of defects and background was obvious. Compared with the national standard inspection method, the detection accuracy of the preparation visual system reached 94.20%, and the detection deviation was not more than 1 preparation grade, which was in high consistency with the national standard inspection results. The detection time of single cotton sample system was 1.2 s, and the detection efficiency was improved by 77.36%. The system can meet the requirements of field use, and provide a technical reference for the instrumental detection of cotton preparation indexes.
  • [1] 卢秀茹,贾肖月,牛佳慧.中国棉花产业发展现状及展望[J].中国农业科学,2018,51(1):26-36.LU Xiuru,JIA Xiaoyue,NIU Jiahui.The present situation and prospects of cotton industry development in China[J].Scientia Agricultura Sinica,2018,51(1):26-36.(in Chinese)
    [2] 国家统计局.国家统计局关于2022年棉花产量的公告[EB/OL].(2022-12-26)[2022-12-31]. http://www.stats.gov.cn/ xxgk/sjfb/zxfb2020/202212/t20221227_1891259.html.
    [3] 中国国家标准化管理委员会.棉花第1部分:锯齿加工细绒棉:GB 1103.1—2012[S].北京:中国标准出版社,2012.
    [4] 布音其其克.棉花颜色级和轧工质量的评定方法及影响因素[J].中国纤检,2019(4):57-58.BU Yinqiqike.Evaluation methods and influencing factors of cotton color grade and ginning quality[J].China Fiber Inspection,2019(4):57-58.(in Chinese)
    [5] 朱云,凌志刚,张雨强.机器视觉技术研究进展及展望[J].图学学报,2020,41(6):871-890.ZHU Yun,LING Zhigang,ZHANG Yuqiang.Research progress and prospect of machine vision technology[J].Journal of Graphics,2020,41(6):871-890.(in Chinese)
    [6]

    MD MORSHEDUL A,ZHU Zanbo,BERNA E T,et al.Automatic assessment and prediction of the resilience of utility poles using unmanned aerial vehicles and computer vision techniques[J].International Journal of Disaster Risk Science,2020,11(1):119-132.

    [7] 宋帅帅,黄锋,江燕斌.基于机器视觉几何量测量技术研究进展分析[J].电子测量技术,2021,44(3):22-26.SONG Shuaishuai,HUANG Feng,JIANG Yanbin.Analysis on the research progress of geometric measurement technology based on machine vision[J].Electronic Measurement Technology,2021,44(3):22-26.(in Chinese)
    [8] 宋国庆,吴育民,冯云鹏,等.机器视觉在光学加工检测中的应用[J].影像科学与光化学,2016,34(1):30-35.SONG Guoqing,WU Yumin,FENG Yunpeng,et al.Application of machine vision in optical manufacturing and testing[J].Imaging Science and Photochemistry,2016,34(1):30-35.(in Chinese)
    [9] 董胜,袁朝辉,谷超,等.基于多学科技术融合的智能农机控制平台研究综述[J].农业工程学报,2017,33(8):1-11.DONG Sheng,YUAN Zhaohui,GU Chao,et al.Research on intelligent agricultural machinery control platform based on multi-discipline technology integration[J].Transactions of the CSAE,2017,33(8):1-11.(in Chinese)
    [10]

    ALEX J C W,JEFFREY B J.Volcano video data characterized and classified using computer vision and machine learning algorithms[J].Geoscience Frontiers,2020,11(5):1789-1803.

    [11] 肖春燕,侯加林.皮棉轧工质量分级模型的建立[J].山东农业科学,2017,49(10):134-138.XIAO Chunyan,HOU Jialin.Building of lint cotton ginning quality grading model[J].Shandong Agricultural Sciences,2017,49(10):134-138.(in Chinese)
    [12] 于红彬,夏彬.基于图像处理的棉花表面杂质自动识别[J].上海纺织科技,2020,48(6):17-19,64.YU Hongbin,XIA Bin.Automatic identification of cotton surface impurities based on image processing[J].Shanghai Textile Science & Technology,2020,48(6):17-19,64.(in Chinese)
    [13] 李晓慧,曹仲庆,陈智勇,等.基于卷积神经网络的棉花轧工质量分级系统研究[J].中国纤检,2021(6):124-126.LI Xiaohui,CAO Zhongqing,CHEN Zhiyong,et al.Research on cotton ginning quality classification system based on convolutional neural network[J].China Fiber Inspection,2021(6):124-126.(in Chinese)
    [14] 黄仰东,邓中民.基于图像处理的原棉疵点识别方法[J].上海纺织科技,2020,48(7):47-50.HUANG Yangdong,DENG Zhongmin.Raw cotton defect recognition method based on image processing[J].Shanghai Textile Science & Technology,2020,48(7):47-50.(in Chinese)
    [15] 李龙.基于改进Mobile-Net-V2的原棉杂质分类方法[J].毛纺科技,2021,49(2):83-88.LI Long.Raw cotton impurity classification method based on improved Mobile-Net-V2[J].Wool Textile Journal,2021,49(2):83-88.(in Chinese)
    [16] 张若宇,陈净,江英兰,等.一种皮棉轧工质量图像采集装置:21502452.7[P].2021-06-15.
    [17] 张若宇,杨萍,宋方丹,等.便携式皮棉轧工质量分级检测装置及方法:10642907.2[P].2022-08-12.
    [18] 吴一全,赵朗月,苑玉彬,等.基于机器视觉的PCB缺陷检测算法研究现状及展望[J].仪器仪表学报,2022,43(8):1-17.WU Yiquan,ZHAO Langyue,YUAN Yubin,et al.Research status and the prospect of PCB defect detection algorithm based on machine vision[J].Chinese Journal of Scientific Instrument,2022,43(8):1-17.(in Chinese)
    [19] 谢秋菊,周红,包军,等.基于机器视觉的畜禽体质量评估研究进展[J].农业机械学报,2022,53(10):1-15.XIE Qiuju,ZHOU Hong,BAO Jun,et al.Review on machine vision-based weight assessment for livestock and poultry[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(10):1-15.(in Chinese)
    [20] 周其洪,彭轶,岑均豪,等.基于机器视觉的细纱接头机器人纱线断头定位方法[J].纺织学报,2022,43(5):163-169.ZHOU Qihong,PENG Yi,CEN Junhao,et al.Yarn breakage location for yarn joining robot based on machine vision[J].Journal of Textile Research,2022,43(5):163-169.(in Chinese)
    [21] 夏杰锋,唐武勤,杨强.光伏航拍红外图像的热斑自动检测方法[J].浙江大学学报(工学版),2022,56(8):1640-1647.XIA Jiefeng,TANG Wuqin,YANG Qiang.Automatic hot spot detection method for photovoltaic aerial infrared image[J].Journal of Zhejiang University (Engineering Science),2022,56(8):1640-1647.(in Chinese)
    [22] 宋泽园,穆光慧,胡美容,等.病理切片疫苗安全性指标自动检测技术[J].分析试验室,2023,42(1):22-32.SONG Zeyuan,MU Guanghui,HU Meirong,et al.Automatic detection of vaccine safety indicators of pathological sections[J].Chinese Journal of Analysis Laboratory,2023,42(1):22-32.(in Chinese)
    [23] 彭睿旻,江军,匡光涛,等.基于EEG的癫痫自动检测:综述与展望[J].自动化学报,2022,48(2):335-350.PENG Ruimin,JIANG Jun,KUANG Guangtao,et al.EEG-based automatic epilepsy detection:review and outlook[J].Acta Automatica Sinica,2022,48(2):335-350.(in Chinese)
    [24] 王谣,李彬华,杨帅明,等.由USB 3相机和GigE相机构建的图像采集系统[J].天文研究与技术,2019,16(4):455-461.WANG Yao,LI Binhua,YANG Shuaiming,et al.Image acquisition system built by USB 3 camera and GigE camera[J].Astronomical Research & Technology,2019,16(4):455-461.(in Chinese)
    [25] 马浩越,刘晶郁,杨炜.车载GigE Vision实时前方车辆防撞预警系统设计[J].中国科技论文,2018,13(10):1120-1126.MA Haoyue,LIU Jingyu,YANG Wei.Design of real-time preceding vehicle collision warning system with mobile GigE Vision[J].China Sciencepaper,2018,13(10):1120-1126.(in Chinese)
    [26] 胡进,查文舒,刘镇领,等.基于图像纹理合成的特征可调控的数字岩心重构方法[J].合肥工业大学学报(自然科学版),2021,44(3):344-349.HU Jin,ZHA Wenshu,LIU Zhenling,et al.Feature-adjustable digital core reconstruction method based on image texture synthesis[J].Journal of Hefei University of Technology (Natural Science),2021,44(3):344-349.(in Chinese)
    [27] 时庆涛,朱兴宇,于超.多光谱图像纹理特征数据挖掘方法仿真[J].计算机仿真,2020,37(2):247-250.SHI Qingtao,ZHU Xingyu,YU Chao.Simulation of multi-spectral image texture feature data intelligent mining method[J].Computer Simulation,2020,37(2):247-250.(in Chinese)
    [28] 石康君,王静安,高卫东.织物褶皱多尺度灰度共生矩阵分析[J].丝绸,2020,57(2):35-40.SHI Kangjun,WANG Jing'an,GAO Weidong.Multi-scale GLCM analysis of fabric wrinkles[J].Journal of Silk,2020,57(2):35-40.(in Chinese)
    [29] 江曼,张皓翔,程德强,等.融合HSV与方向梯度特征的多尺度图像检索[J].光电工程,2021,48(11):64-76.JIANG Man,ZHANG Haoxiang,CHENG Deqiang,et al.Multi-scale image retrieval based on HSV and directional gradient features[J].Opto-Electronic Engineering,2021,48(11):64-76.(in Chinese)
    [30] 唐超.HSV空间的多尺度Retinex低照图像增强[J].实验室研究与探索,2022,41(5):54-59.TANG Chao.Low illumination image enhancement based on multiscale Retinex in HSV space[J].Research and Exploration in Laboratory,2022,41(5):54-59.(in Chinese)
计量
  • 文章访问数:  0
  • HTML全文浏览量:  0
  • PDF下载量:  0
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-03-20
  • 刊出日期:  2023-11-24

目录

    /

    返回文章
    返回