面向摄像整纬装置的多源图像处理与融合的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
我国是纺织品生产大国,纺织业是我国的传统出口行业。随着中国加入WTO,纺织产品的出口量越来越大;且随着国内生活水平的不断提高,内销产品也对纬斜指标的要求越来越高。因此,国内用户对高性能的整纬装置的需求十分迫切,前景十分广阔。
     本文面向摄像整纬装置中基于织物图像纹理的纬斜检测与多摄像头图像信息的融合与处理问题,综合运用数字图像处理、模式识别以及信息融合等技术,设计了多摄像头纬斜检测的架构,提出了基于图像处理的织物纹理识别算法和面向摄像整纬的多源图像融合算法,为摄像整纬装置的研制提供支持。
     首先,论文从图像纹理辨识技术、多传感器信息集成与融合、DSP处理器的发展等三方面,对摄像整纬装置研发的理论依据进行了分析,并提出了多摄像头纬斜检测的基本架构。
     其次,基于图像处理的织物纹理识别算法,以傅氏变换的自配准性质,结合基于统计的纹理自动分析方法,对织物纹理图像进行识别与特征提取,计算得到其纹理的方向特征参数。
     接着,针对摄像整纬装置中多摄像头图像信息的融合问题,提出了面向摄像整纬的多源图像融合算法。通过对整纬执行机构的矫正辊(直辊和弯辊)调整织物行程差的作用进行数字化处理,应用数据拟合等方法,实现对多摄像头织物纹理的方向特征参数的信息融合与处理,从而得到织物当前的纬斜状态与纬斜程度,为整纬装置的执行机构提供必要的控制依据。
     然后,应用基于图像处理的织物纹理识别算法,结合多摄像头纬斜检测的基本架构,提出了织物图像采集与纹理识别的实现方案,对摄像整纬装置中织物图像采集与纹理识别部分进行了初步的硬件架构与软件流程设计。
     最后,对本文的研究工作进行了总结,并展望了其进一步研究的方向。
As a large textile producer, textile industry has become a traditional export industry in China. The volume of textile products has kept growing since China entered WTO. Meanwhile, domestic customers are paying more and more attention to weft-inclining parameters with the improvement in standard of living. Therefore, high-powered weft-straightening machines are urgently demanded within China and thus have a bright foreground.
     In order to solve the problem of fabric texture image identification and multi-camera image information fusion, we design an architecture for multi-CCD weft-straightening based on digital image processing, pattern recognition and information fusion We also suggest a fabric texture image identification algorithm and a multi-image fusion algorithm CCD-based weft-straightening machine, which could be a reference for further study on the research and development of this kind of machine.
     Firstly, we analyze the theory foundation for research and development of CCD-based weft-straightening devices based on image texture identification, multi-sensor information fusion and DSP technology. And then we propose a framework for multi-camera fabric-inclining detection. Secondly, with the auto-registration property of Fourier transformand texture automatic recognition method based on statistics, we calculate the main parameters for texture direction of a fabric and extract its characters.
     Thirdly, amulti-image fusion algorithm for CCD-based weft-straightening machines is proposed to implement multi-camera information fusion on them. It digitalizes the action of the straightener rolls, the erect roller and the bowed roller, of the machine's actuator which leads a progressive error to the fabric and then fuses the direction character parameters of multiple fabric textures. It gets the weft-declining status and extends of the fabric at the moment so as to provide the actuator with necessary parameters for controlling.
     And then we suggest a solution for fabric image gathering and texture identification with the fabric texture image identification algorithm and the architecture for milti-camera fabric-inclining detection. We also study on an elementary hardware and software design for fabric image gathering and identification subsystem of the CCD-based weft-straightening machine.
     Finally, we summarize all our research and prospect its further research topics.
引文
[1] 唐家辉,微机旋转探头式光电整纬装置的研究[J],电气传动自动化,2001,23(1):41-46
    [2] 蓝国兴,艾克武,信息融合技术,计算机世界报,1997,(18)
    [3] 金剑秋,王章野,彭群生,相关系数准则下的多光谱图像最优融合方法,计算机辅助设计与图形学学报,2004,16(12):1656-1661
    [4] 熊莉,多设备医学图像信息融合技术,中华现代影响学杂志,2005,2(9):816-817
    [5] 纺机制造大国再次向全球展现新貌,中国纺织网.咨询,2004-10-12
    [6] 国产纺织仪器业向高端产品领域发展,中国纺织网-咨询,2005-07-21
    [7] 中国纺织总会,机织物与针织物纬斜和弓纬试验方法,中华人民共和国国家标准[S],GB/T 14801—93
    [8] 吴周林,SP04型整纬机针轮滑移装置的改进[J],纺织器材,2002,29(6):373-374
    [9] 曹砚军,光电整纬机的研制[J],潍坊学院学报,2004,4(2):77-78
    [10] Q/320400CLlol8-1999,电脑光电整纬装置企业标准[S]
    [11] 唐家辉,采用STD总线的旋转探头式光电整纬装置的研制[J],电子与自动化,2000(1):30-34
    [12] 周正元,SYH625型光电整纬装置的设计开发[J],河海大学常州分校学报,2003,17(2):47-50
    [13] 汤新臣,郭国林,虞剑,王克鸿,徐越兰,光学传感技术在熔池信息监测中的应用[J],机械制造于研究,2003,(6):62-65
    [14] 闵庆凯,日野泰成,焊接机器人智能过程与控制[J],焊接技术,2003,32(2):42-43
    [15] 蔡智勇,张华,蒋水清,基于图像传感器的焊缝偏差信息提取方法[J],传感器技术,2003,22(8):35-37
    [16] 潘锋,阎镭,向桂山,梁冬泰,王宣银,基于机器视觉技术的气动系统状态监控与故障诊断[J],机床与液压,2005,(8):203-205
    [17] 熊超,田小芳,陆起涌,嵌入式机器视觉系统设计[J],仪器仪表学报,2005,26(8):368-370
    [18] 李朝晖主编,数字图像处理及应用[M],北京:机械工业出版社,2004,6:156-157
    [19] 任洪娥,关明山,马岩,板材的纹理识别初探[J],木材加工机械,2004,(1):5-8
    [20] 庄国瑜,孙悦,织物纹理计算机图像处理的多频道分解方法[J],天津工业大学学报,2001,20(3):27-29
    [21] 冯志林,尹建伟,石慧,陈刚,董金祥,提花织物纹理的Allen-Cahn水平集去噪方法[J],计算机辅助设计与图形学学报,2004,16(8):1033-1039
    [22] 王伟华,王成焘,磨粒图像的纹理分析及识别[J],上海交通大学学报,2004,38(6):874-876
    [23] 杨旭红,李栋高,何蕾,绉织物表面图像的分形特征分析[J],纺织学报,2003,24(4):319-321
    [24] 汪成龙,李晶,高晓丁,高效能的织物疵点识别算法及其实现[J],棉纺织技术,2004,32(6):343-346
    [25] 韩伟红,黄子中,沈清,基于神经网络和傅氏变幻的指纹自动分类系统[J],计算机应用与软件,2000,17(3):33-39
    [26] Xiaoming Peng , Mingyue Ding, Chengping Zhou, Qian Ma, Apractical two-step image registration method for two-dimensional images[J], Information Fusion, 2004, 5:283-298
    [27] Susanta Mukhopadhyay, Bhabatosh Chanda, Fusion of2D grayscale images using multiscale morphology[J], Pattern Recognition, 2001, 34:1939-1949
    [28] Tania S. Douglas, Image processing for craniofacial landmark identification and measurement: A review ofphotogrammetry and cephalometry[J], Computerized Medical Imaging and Graphics, 2004, 28:401-409
    [29] Michel A. Audette, Frank P. Ferric, Terry M. Peters, An algorithmic overview of surface registration techniques for medical imaging[J], Medical Image Analysis, 2000, 4:201-217
    [30] 沈晋慧,马斌荣,杨虎,基于小波分析的医学图像融合技术及其效果评价[J],中国医学物理学杂志,2003,20(4):232-234
    [31] 马云芳,王小华,基于小波理论的织物纹理特征提取[J],杭州电子工业学院学报,2002,22(6):85-88
    [32] 陈梅,刘峰,基于神经网络的纹理识别技术[J],贵州大学学报(自然科学版),2003,20(4):400-406
    [33] 郑肇葆,遗传算法与单纯形法组合的影像纹理分类方法[J],测绘学报,2003,32(4):325-329
    [34] 周越,许晴,基于隐马尔可夫复合树模型的图像纹理分析[J],数据采集与处理,2004,19(4):405-410
    [35] 张震宇,陈怀楚,曹亦明,刘伟,一种利用图像邻域信息进行边界光滑的纹理识别的方法[J],计算机应用,2004,24(12):25-27
    [36] Hongjie Xie, Nigel Hicks, G. Randy Keller, Haitao Huang, Vladik Kreinovich, An IDL/ENVI implementation of the FFT-based algorithm for automatic image registration[J], Computers & Geosciences, 2003, 29:1045-1055
    [37] 王文惠,孟兵,万建伟,周良柱,利用不变量进行基于内容的图像检索[J],电子学报,2002,30(7):949-951
    [38] 罗罡,林列,方志良,方晖,母国光,多通道编码摄影中的数字化白光信息处理[J],仪器仪表学报,2002,21(4):376-340
    [39] 王东峰,邹谋炎,傅氏变换的自配准性质及其在纹理识别和图象分割中的应用[J],中国图象图形学报,2003,8(A)(2):140-146
    [40] J. Borkowski, B. J. Matuszewski, J. Mroczka, L.-K. Shark, Geometric matching of circular features by least squares fitting[J], Pattern Recognition Letters, 2002, 23:885-894
    [41] Huzefa Neemuchwala, Alfred Hero, Paul Carson, Image matching using alpha-entropy measures and entropic graphs[J], Signal Processing, 2005, 85: 277-296
    [42] Zheng Liu, Yeong Khing Ho, Kazuhiko Tsukada, Koichi Hanasaki, Yaping Dai, Lingqi Li, Using multiple orientational filters of steerable pyramid for image registration[J], Information Fusion, 2002, 3: 203-214
    [43] Xiaohui Yuan, Jian Zhang, Bill P. Buckles, Evolution strategies based image registration via feature matching[J], Information Fusion, 2004, 5:269-282
    [44] Barbara Zitova, Jan Flusser, Image registration methods: A survey[J], Image and Vision Computing, 2003, 21:977-1000
    [45] 周超超,张永志,程胜文,神经网络在多传感器信息集成与融合中的应用[J],传感器技术,2002,11:49-51
    [46] 夏明革,何友,黄晓冬,夏仕昌,多传感器图像融合应用评述[J],舰船电子对抗,2002,25(5):38-44
    [47] 夏明革,何友,欧阳文,像素级图像融合方法与融合效果评价[J],遥感技术与应用,2002,17(4):224-229
    [48] Gonzalo Pajares, Jesus Manuel de la Cruz, A wavelet-based image fusion tutorial[J], Pattern Recognition, 2004, 37:1855-1872
    [49] 郭志强,多源图像融合的方法及评价[J],国外建材科技,2003,23(1):53-55
    [50] 夏明革,何友,唐小明,夏仕昌,图像融合的发展现状与展望[J],舰船电子工程,2002,6:2-14
    [51] Shutao Li, James T.Kwok, Yaonan Wang, Combination of images with diverse focuses using the spatial frequency[J], Information Fusion, 2001, 2:169-176
    [52] A panoramic sampling of avant-garde applications of information fusion[J], Information Fusion, 2004, 5:233-238
    [53] 冯大一,何先平,闰云娟,多源遥感数字图像融合评价[J],太原师范学院学报(自然科学版),2003,2(4):5-7
    [54] 谷口庆治编,朱虹等译,数字图像处理——应用篇,北京:科学出版社[M],2002,43-48
    [55] 范松林,计算机数字图像分析在非织造结构检测中的应用(上)[J],北京纺织,2004,25(3):10-14
    [56] 张雄伟,邹霞,贾冲,DSP芯片原理与应用[M],北京:机械工业出版社,2005
    [57] 章之江,单面纬编织物纵向歪斜的产生与控制[J],针织工业,1997
    [58] 蒋玉花,许嘉宁,如何控制牛仔布后整理中的整纬[J],化纤与纺织技术, 2003,4:16-18
    [59] 张卫宁,DSPs原理及应用[M],北京:国防工业出版社,2002
    [60] 胡良剑,丁晓东,孙晓君,数学实验——使用MATLAB[M],上海:上海科学技术出版社,2001

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700