抗抖动双向K级容错棒材计数系统研究
|
摘要
中南大学信息科学工程学院与涟源钢铁集团公司合作研制的基于视觉的在线棒材计数系统取得了很大成功,并在多个棒材厂推广使用。然而,在现实生产使用过程中也暴露出一些急需解决的技术问题。
针对在计数系统中遇到的棒材识别率较低的问题,首先提出了序贯性滤波的重度模糊作为阈值图像对图像进行多局部阈值分割,消除了由于棒材端面照度不均匀造成的分割不均匀的缺点;然后对中心增强中不适应毛刺的缺点,采用在算法前进行模糊消除其不圆度,在算法后进行模糊以消除其毛刺,提高了中心增强后各个团块的独立性和团块性;最后对多次聚类中由于桶聚类不能保证聚类完成和不是最优聚类等自身的缺点,采用在团块性好时采用桶聚类方法,在团块性差时采用最短距离聚类方法,不但保证了聚类的速度,并提高了聚类的精度,保证了棒材识别中心位置点的准确性。
针对偶尔出现链床运行不平稳而造成的棒材抖动等问题,本文根据棒材生产的计数特点,在现有的基于总体偏移量对位算法、基于分段偏移量对位算法以及基于积分对位等这些基于投影的多目标匹配的基础上,提出综合投影匹配和特征点模式的多方法融合的匹配模式,保证了匹配的准确性。
针对在某些钢铁厂出现的链床双向运行这种特殊的情况,在原有单向K级计数模式的基础上,提出了双向K级计数的计数模式。当链床正向运行时计数值增加,反向运行时计数值减少,从而避免了同一根棒材多次经过计数系统而造成的重复计数。
试验证明,经过算法改进,提高了在线棒材计数系统的识别正确率和跟踪准确率,同时达到了双向计数的目的。
The vision-based online steel bar counting system co-researched by Lianyuan Iron and Steel Group CO. Ltd and Central South University has achieved considerable success in some bar plants. However, a number of technical issues needed to be addressed urgently has also revealed in the use of the real production process.
For the low recognition rate in the bar counting system, first in order to solve the problem of uneven division caused by asymmetric illumination of the bar ends, the thesis uses severe fuzzy image of sequential filtering as a threshold image to segment image by multi-thresholds method and eliminate the shortcomings; second in order to solve the problem of unsuitability of burr in the center enhanced algorithm, the thesis uses moderate fuzzy to eliminate non-circularity before the algorithm starts and after the algorithm to erase flash burr to increase each block mass' independence and coherency; last to improve the drawback of classical bucket-clustering is not a best clustering and can not guarantee accomplishment of the clustering in the multiple clustering, the thesis propose to use bucket-clustering when crumby and use minimum-distance clustering and guarantee the accuracy of the steel bars' center.
In order to solve the problem of bounce of steel bar generated by chain moves jiggly, the thesis proposes a synthesis method of projection matching and characteristic points pattern based on original method such as universe slippage matching, sectionalize slippage matching and integral matching and so on according to steel bar's counting feature. The test proves that these improvements can guarantee the accuracy.
In order to solve the special situation of Chain bed two-way movement in some plants, the paper proposes bidirectional K-level counting model based on original K-level unidirectional counting model. When the chain bed moves forward the count value increases, otherwise the count value decreases. In this way it avoids the situation that the identical steel bar is counted repeatedly because of multiple passing the counting system.
The test proves that the accuracy of recognition as well as the tracking of the on-line visual counting system has been improved and meanwhile achieves the bidirectional counting goal after improvement.
针对在计数系统中遇到的棒材识别率较低的问题,首先提出了序贯性滤波的重度模糊作为阈值图像对图像进行多局部阈值分割,消除了由于棒材端面照度不均匀造成的分割不均匀的缺点;然后对中心增强中不适应毛刺的缺点,采用在算法前进行模糊消除其不圆度,在算法后进行模糊以消除其毛刺,提高了中心增强后各个团块的独立性和团块性;最后对多次聚类中由于桶聚类不能保证聚类完成和不是最优聚类等自身的缺点,采用在团块性好时采用桶聚类方法,在团块性差时采用最短距离聚类方法,不但保证了聚类的速度,并提高了聚类的精度,保证了棒材识别中心位置点的准确性。
针对偶尔出现链床运行不平稳而造成的棒材抖动等问题,本文根据棒材生产的计数特点,在现有的基于总体偏移量对位算法、基于分段偏移量对位算法以及基于积分对位等这些基于投影的多目标匹配的基础上,提出综合投影匹配和特征点模式的多方法融合的匹配模式,保证了匹配的准确性。
针对在某些钢铁厂出现的链床双向运行这种特殊的情况,在原有单向K级计数模式的基础上,提出了双向K级计数的计数模式。当链床正向运行时计数值增加,反向运行时计数值减少,从而避免了同一根棒材多次经过计数系统而造成的重复计数。
试验证明,经过算法改进,提高了在线棒材计数系统的识别正确率和跟踪准确率,同时达到了双向计数的目的。
The vision-based online steel bar counting system co-researched by Lianyuan Iron and Steel Group CO. Ltd and Central South University has achieved considerable success in some bar plants. However, a number of technical issues needed to be addressed urgently has also revealed in the use of the real production process.
For the low recognition rate in the bar counting system, first in order to solve the problem of uneven division caused by asymmetric illumination of the bar ends, the thesis uses severe fuzzy image of sequential filtering as a threshold image to segment image by multi-thresholds method and eliminate the shortcomings; second in order to solve the problem of unsuitability of burr in the center enhanced algorithm, the thesis uses moderate fuzzy to eliminate non-circularity before the algorithm starts and after the algorithm to erase flash burr to increase each block mass' independence and coherency; last to improve the drawback of classical bucket-clustering is not a best clustering and can not guarantee accomplishment of the clustering in the multiple clustering, the thesis propose to use bucket-clustering when crumby and use minimum-distance clustering and guarantee the accuracy of the steel bars' center.
In order to solve the problem of bounce of steel bar generated by chain moves jiggly, the thesis proposes a synthesis method of projection matching and characteristic points pattern based on original method such as universe slippage matching, sectionalize slippage matching and integral matching and so on according to steel bar's counting feature. The test proves that these improvements can guarantee the accuracy.
In order to solve the special situation of Chain bed two-way movement in some plants, the paper proposes bidirectional K-level counting model based on original K-level unidirectional counting model. When the chain bed moves forward the count value increases, otherwise the count value decreases. In this way it avoids the situation that the identical steel bar is counted repeatedly because of multiple passing the counting system.
The test proves that the accuracy of recognition as well as the tracking of the on-line visual counting system has been improved and meanwhile achieves the bidirectional counting goal after improvement.
引文
[1]罗三定,沙莎,沈德耀,等.棒材生产在线视觉计数系统研究[J].小型微型计算机系统,2004,25(4):671-675.
[2]罗三定,李弟平.K级容错计数算法的设计与实现[J].计算机工程与应用,2004,16(8):95-97.
[3]Otsu N.Discriminant and least square threshold selection[J].In:Proc 4IJCPR,1978:592-596..
[4]Otsu N.A threshold selection method from gray-level histogram[J].IEEE Trans.on System,Man and Cybernetics,1978,8:62-66.
[5]KAPURJN,SAHOOPK,WONGAKC.A new method for gray-level picture thresholding using the entropy of the histogram[J].Computure Graphics,Vision and Image Processing,1985(29):273-285.
[6]SAHOOP,WlLKINSOGC.YEAGERJ.Threshold selection using Renyi's entropy [J].Pattern Recognition,1997,30(1):71-84.
[7]王祥科,郑志强.Otsu多阈值快速分割算法及其在彩色图像中的应用[J].计算机应用,2006,6(26):14-15.
[8]陈宇,庞全.局部自适应的细胞图像分割方法[J].杭州电子科技大学学报,2005,25(4):57-60.
[9]邢延超,谈正.基于多阈值融合的图像分割[J].计算机学报,2004(2),27(2):253-256.
[10]王培珍,杨维翰,沈玉梁.基于融合技术的棒材定支数图像识别[J].合肥工业大学学报(自然科学版),2003,26(2):197-199.
[11]Hallard D H.Generalizing the Hough transform to detect arbi-trary shapes[J].Pattern Recognition,1981,13(2):111-122.
[12]Xu L,Oja E.A new curve detection method:Randomized Hough transform(RHT)[J].Pattern Recognition Letters,1990,11(5):331-338.
[13]Shu Zhilin,Qi Feihu.A novel algorithm for fast circle detectionusing randomized Hough transform[J].Computer Engineering,2003,29(6):87-89.
[14]Yuan Weipeng,Shi Pengfei.A new improvement of randomized Hough transform based on fuzzy theory[J].Journal of Shanghai Jiaotong University,2002,36(12):1825-1828.
[15]于中,徐文立,陈峰.边缘图像中圆形轮廓的两步法检测[J].计算机辅助设计与图形学学报,2005,17(2):243-246.
[16]李江涛,倪国强.一种快速准确识别圆形目标的新算法[J].激光与红外,2007,37(6):575-578.
[17]杨煊.在线视觉棒材计数分钢研究:[硕士学位论文].长沙:中南大学,2005.
[18]罗三定,肖飞.不规则类圆形团块目标图像识别的新方法[J].中南大学学报(自然科学版),2004,35(4):632-637.
[19]Zhao T,Nevatia R.Tracking multiple humans in crowded environment[C].CVPR,Washington DC,2004,(2):406-413.
[20]梁冰洪,炳熔,曙光.一种基于光流计算的机器人视觉与行为模型[J].宇航学报,2003,24(5):643-647.
[21]李海明,陈新,吴芳,等.复杂背景下运动目标的光流区域提取方法[J].福州大学学报,2001,29(4):101-106.
[22]任清论,朱方文.一种用于目标跟踪的人工特征点提取算法[J].机电一体化,2004,2(3):30-33.
[23]汪亚明,楼正国,卞听,等.一种非刚体运动图象序列的特征点对应方法[J].中国图象图形学报,2000,5(3):232-236.
[24]朱方文,李德强,袁政鹏,等.基于共面标记点的AR跟踪系统[J].上海大学学报,2004,10(5):458-462.
[25]Jung S K,Wohn K Y.A model-based 3-D tracking of rigid objects from a sequence of multiple perspective views[J].Pattern Recognition Letters.1998,(19):499-512.
[26]薛建儒,郑南宁,钟小品.多目标跟踪的序贯分层抽样信任传播算法[J].中国科学(E辑信息科学),2005,35(10):1049-1063.
[27]林顺洪,朱新才.棒材在线计数系统的研制[J].检测与仪表,2007,(4):41-44.
[28]徐科.棒材自动计数系统.中国,发明专利申请公丌说明书,申请号:03100566.7,公开号:CN1424700A.
[29]李朴,孙运芝.轧钢车间打捆计数装置研究[J].仪器仪表与分析监测,2003,(2):11-12.
[30]周群,胡光锐.基于模板覆盖法的钢筋在线计数方法[J].上海交通:大学学报,1999,33(11):1462-1464.
[31]宋强,徐科.基于图像处理的棒材自动计数技术[J].钢铁,2004,39(5):34-37.
[32]Marie-Pierre Dubuisson Jolly,Sridhar Lakshmanan,and Anil K.Jain.Vehicle Segmentation and Classification Using Deformable Templates[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1996,18(3):293-308.
[33]Swanson M D,Tewfik A H.Fast Progressively Refined Image Retrieval.Joumal of Electronic Imaging,1998,7(3):443-452.
[34]Tian B,Shaikh M A,Azimi-Sadjadi M R,etal.A Study of Cloud Classification With Neural Networks Using Spectral and Textural Features.IEEE Trans.Neural Networks,1999,10(1):138-151.
[35]陈哲,冯天谨.基于小波分形特征提取的图像分割方法[J].中国图象图形学报,1999,4A(12):1072-1077.
[36]杨杰,付忠良.照度不均匀图像的快速自适应狄度修正[J].计算机应用,2005,25(3):598-601.
[37]李了了.基于大津法的图像分块二值化算法[J].微计算机信息,2005,21(8-3):76-77.
[38]王丙文.模糊阈值分割算法在具有双峰直方图图像中的应用[J].现代电子技术,2001,10:3-5.
[39]崔冰.基于统计模式识别的岩石节理图像分割方法[J].计算机工程与应用,2006,10:213-215.
[40]冈萨雷斯.数字图像处理(第二版)[M].北京:电子工业出版社,2002.
[41]GAO Yang,LI Yan-jun,ZHANG Ke.Anisotropic Piecewise Gaussian Filter of Infrared Image[J].ACTA PHOTONICA S INICA,2007(6),36(6):1167-1169.
[42]万洪晓,汤井田,唐艳.一种线性滤波算子在医学扫描图像中的应用[J].中国医学物理学杂志,2007(7),24(4):251-253.
[43]李秀峰,苏兰海.基于中值滤波和数字形态学的图像边缘检测[J].计算机与信息技术,2007(7),24(4):251-253.
[44]马学磊,商泽利.基于噪声点检测的中值滤波方法[J].电子技术,2008(1):150-153.
[45]陈万海,赵春晖.基于高斯低通滤波的超光谱遥感图像分类研究[J].黑龙江大学自然科学学报,2007(12),24(6):751-754.
[46]郭海霞,解凯.一种改进的自适应中值滤波算法[J].中国图象图形学报,2007(7),12(7):1185-1188.
[47]张霞,葛芦生.自适应中值滤波算法的研究与应用[J].微计算机信息,2007,23(2-3):217-220.
[48]郑柏杰.基于划分的聚类算法研究:[工程硕士学位论文].重庆:重庆大学,2005.
[49]淦文燕,李德毅,王建民.一种基于数据场德层次聚类方法[J].电子学报,2006(2),2:258-260.
[50]蔡伟鸿,刘震.基于密度聚类算法德入侵检测研究[J].计算机工程与应用,2005,(21):149-150.
[51]刘敏娟,柴玉梅,张西芝.基于相似度德网格聚类算法[J].计算机工程与应用,2007,43(7):198-200.
[52]Francois G.Meyer,Patrick Bouthemy.Region-based tracking using a fine motion models in long image sequences[J].Computer Vision,Graphics,and Image Processing,1994,60(2):119-140.
[53]Jonathan Owens,Andrew Hunter,Eric Fletcher.A Fast Model-Free Morphology-Based Object Tracking Algorithm[J].IEEE Conference on Computer Vision and Pattern Recognition,2002,56(4):767-776.
[54]Francois G.Meyer,Patrick Bouthemy.Region-based tracking using a fine motion models in long image sequences[J].Computer Vision,Graphics,and Image Processing,1994,60(2):19-140.
[55]江小平,章胜勤,姚天任,等.数字视频监控系统在MSTP上的实现[J].计算机工程与应用,2005,34(4):200-202.
[56]谢韬,何芸,冯重熙.人脸部特征自动定位及其在图像编码中的应用[J].清华大学学报,1999,39(5):81-84.
[57]A.Eleftheriadis,A.Jacquin.Automatic Face Location Detection and Tracking for Model-Assisted Coding of Video Teleconference Sequences at Low Bit Rates[J].Signal Processing - Image Communication,1995,7(3):231-248.
[58]洪宇,高广珠,余理富,等.一种基于动态背景的运动车辆跟踪算法[J].计算机应用研究,2004,6(5):107-109.
[59]Su Jianbo,Xi Yugeng,Tang shantung.Planar Motion Tracking with an Uncalibrated Robort/Vision System[J].Systems Engineering and Electronics,1998,9(4):45-50.
[60]欧宗瑛,袁野,张艳珍.基于颜色信息足球机器人视觉跟踪算法[J].大连理工大学学报,2000,40(6):729-732.
[61]蒋平,沈世锦,陈辉堂,等.基于图像误差的机器人运动目标自适应跟踪[J].机器人,1997,19(6):431-437.
[62]常红,王涌天等.基于计算机视觉技术的手形手位跟踪方法[J].北京理工大学学报,1999,19(6):739-743.
[63]张莉,吴剑锋,林强.B超心脏序列图像左室短轴轮廓曲线的动态跟踪[J].福州大学学报,2000,28(6):22-25.
[64]胡匡祜,苏万芳,李翊华,等.运动红细胞形变结构的图像自动定量分析的研 究[J].生物物理学报,1994,10(3):387-392.
[65]潘春荣,郑黎明.点模式匹配在羽毛弯度测量中的应用[J].计算机测量与控制,2007,15(2):172-173.
[66]曾英,王国才,李涛.一种新的点模式指纹匹配算法[J].计算机测量与控制,2007,15(7):959-961.
[67]杨红,唐健.一种基于可变限界盒的指纹匹配算法[J].沈阳工业学院学报,2003(12),22(4):9-12.
[68]罗三定,崔振峰,沙莎.一种实时多目标跟踪的新算法[J].计算机测量与控制,2006,14(8):1108-1109.
[69]崔振峰.棒材图像高效识别算法与容错性能研究:[硕士学位论文].长沙:中南大学,2006.
[2]罗三定,李弟平.K级容错计数算法的设计与实现[J].计算机工程与应用,2004,16(8):95-97.
[3]Otsu N.Discriminant and least square threshold selection[J].In:Proc 4IJCPR,1978:592-596..
[4]Otsu N.A threshold selection method from gray-level histogram[J].IEEE Trans.on System,Man and Cybernetics,1978,8:62-66.
[5]KAPURJN,SAHOOPK,WONGAKC.A new method for gray-level picture thresholding using the entropy of the histogram[J].Computure Graphics,Vision and Image Processing,1985(29):273-285.
[6]SAHOOP,WlLKINSOGC.YEAGERJ.Threshold selection using Renyi's entropy [J].Pattern Recognition,1997,30(1):71-84.
[7]王祥科,郑志强.Otsu多阈值快速分割算法及其在彩色图像中的应用[J].计算机应用,2006,6(26):14-15.
[8]陈宇,庞全.局部自适应的细胞图像分割方法[J].杭州电子科技大学学报,2005,25(4):57-60.
[9]邢延超,谈正.基于多阈值融合的图像分割[J].计算机学报,2004(2),27(2):253-256.
[10]王培珍,杨维翰,沈玉梁.基于融合技术的棒材定支数图像识别[J].合肥工业大学学报(自然科学版),2003,26(2):197-199.
[11]Hallard D H.Generalizing the Hough transform to detect arbi-trary shapes[J].Pattern Recognition,1981,13(2):111-122.
[12]Xu L,Oja E.A new curve detection method:Randomized Hough transform(RHT)[J].Pattern Recognition Letters,1990,11(5):331-338.
[13]Shu Zhilin,Qi Feihu.A novel algorithm for fast circle detectionusing randomized Hough transform[J].Computer Engineering,2003,29(6):87-89.
[14]Yuan Weipeng,Shi Pengfei.A new improvement of randomized Hough transform based on fuzzy theory[J].Journal of Shanghai Jiaotong University,2002,36(12):1825-1828.
[15]于中,徐文立,陈峰.边缘图像中圆形轮廓的两步法检测[J].计算机辅助设计与图形学学报,2005,17(2):243-246.
[16]李江涛,倪国强.一种快速准确识别圆形目标的新算法[J].激光与红外,2007,37(6):575-578.
[17]杨煊.在线视觉棒材计数分钢研究:[硕士学位论文].长沙:中南大学,2005.
[18]罗三定,肖飞.不规则类圆形团块目标图像识别的新方法[J].中南大学学报(自然科学版),2004,35(4):632-637.
[19]Zhao T,Nevatia R.Tracking multiple humans in crowded environment[C].CVPR,Washington DC,2004,(2):406-413.
[20]梁冰洪,炳熔,曙光.一种基于光流计算的机器人视觉与行为模型[J].宇航学报,2003,24(5):643-647.
[21]李海明,陈新,吴芳,等.复杂背景下运动目标的光流区域提取方法[J].福州大学学报,2001,29(4):101-106.
[22]任清论,朱方文.一种用于目标跟踪的人工特征点提取算法[J].机电一体化,2004,2(3):30-33.
[23]汪亚明,楼正国,卞听,等.一种非刚体运动图象序列的特征点对应方法[J].中国图象图形学报,2000,5(3):232-236.
[24]朱方文,李德强,袁政鹏,等.基于共面标记点的AR跟踪系统[J].上海大学学报,2004,10(5):458-462.
[25]Jung S K,Wohn K Y.A model-based 3-D tracking of rigid objects from a sequence of multiple perspective views[J].Pattern Recognition Letters.1998,(19):499-512.
[26]薛建儒,郑南宁,钟小品.多目标跟踪的序贯分层抽样信任传播算法[J].中国科学(E辑信息科学),2005,35(10):1049-1063.
[27]林顺洪,朱新才.棒材在线计数系统的研制[J].检测与仪表,2007,(4):41-44.
[28]徐科.棒材自动计数系统.中国,发明专利申请公丌说明书,申请号:03100566.7,公开号:CN1424700A.
[29]李朴,孙运芝.轧钢车间打捆计数装置研究[J].仪器仪表与分析监测,2003,(2):11-12.
[30]周群,胡光锐.基于模板覆盖法的钢筋在线计数方法[J].上海交通:大学学报,1999,33(11):1462-1464.
[31]宋强,徐科.基于图像处理的棒材自动计数技术[J].钢铁,2004,39(5):34-37.
[32]Marie-Pierre Dubuisson Jolly,Sridhar Lakshmanan,and Anil K.Jain.Vehicle Segmentation and Classification Using Deformable Templates[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1996,18(3):293-308.
[33]Swanson M D,Tewfik A H.Fast Progressively Refined Image Retrieval.Joumal of Electronic Imaging,1998,7(3):443-452.
[34]Tian B,Shaikh M A,Azimi-Sadjadi M R,etal.A Study of Cloud Classification With Neural Networks Using Spectral and Textural Features.IEEE Trans.Neural Networks,1999,10(1):138-151.
[35]陈哲,冯天谨.基于小波分形特征提取的图像分割方法[J].中国图象图形学报,1999,4A(12):1072-1077.
[36]杨杰,付忠良.照度不均匀图像的快速自适应狄度修正[J].计算机应用,2005,25(3):598-601.
[37]李了了.基于大津法的图像分块二值化算法[J].微计算机信息,2005,21(8-3):76-77.
[38]王丙文.模糊阈值分割算法在具有双峰直方图图像中的应用[J].现代电子技术,2001,10:3-5.
[39]崔冰.基于统计模式识别的岩石节理图像分割方法[J].计算机工程与应用,2006,10:213-215.
[40]冈萨雷斯.数字图像处理(第二版)[M].北京:电子工业出版社,2002.
[41]GAO Yang,LI Yan-jun,ZHANG Ke.Anisotropic Piecewise Gaussian Filter of Infrared Image[J].ACTA PHOTONICA S INICA,2007(6),36(6):1167-1169.
[42]万洪晓,汤井田,唐艳.一种线性滤波算子在医学扫描图像中的应用[J].中国医学物理学杂志,2007(7),24(4):251-253.
[43]李秀峰,苏兰海.基于中值滤波和数字形态学的图像边缘检测[J].计算机与信息技术,2007(7),24(4):251-253.
[44]马学磊,商泽利.基于噪声点检测的中值滤波方法[J].电子技术,2008(1):150-153.
[45]陈万海,赵春晖.基于高斯低通滤波的超光谱遥感图像分类研究[J].黑龙江大学自然科学学报,2007(12),24(6):751-754.
[46]郭海霞,解凯.一种改进的自适应中值滤波算法[J].中国图象图形学报,2007(7),12(7):1185-1188.
[47]张霞,葛芦生.自适应中值滤波算法的研究与应用[J].微计算机信息,2007,23(2-3):217-220.
[48]郑柏杰.基于划分的聚类算法研究:[工程硕士学位论文].重庆:重庆大学,2005.
[49]淦文燕,李德毅,王建民.一种基于数据场德层次聚类方法[J].电子学报,2006(2),2:258-260.
[50]蔡伟鸿,刘震.基于密度聚类算法德入侵检测研究[J].计算机工程与应用,2005,(21):149-150.
[51]刘敏娟,柴玉梅,张西芝.基于相似度德网格聚类算法[J].计算机工程与应用,2007,43(7):198-200.
[52]Francois G.Meyer,Patrick Bouthemy.Region-based tracking using a fine motion models in long image sequences[J].Computer Vision,Graphics,and Image Processing,1994,60(2):119-140.
[53]Jonathan Owens,Andrew Hunter,Eric Fletcher.A Fast Model-Free Morphology-Based Object Tracking Algorithm[J].IEEE Conference on Computer Vision and Pattern Recognition,2002,56(4):767-776.
[54]Francois G.Meyer,Patrick Bouthemy.Region-based tracking using a fine motion models in long image sequences[J].Computer Vision,Graphics,and Image Processing,1994,60(2):19-140.
[55]江小平,章胜勤,姚天任,等.数字视频监控系统在MSTP上的实现[J].计算机工程与应用,2005,34(4):200-202.
[56]谢韬,何芸,冯重熙.人脸部特征自动定位及其在图像编码中的应用[J].清华大学学报,1999,39(5):81-84.
[57]A.Eleftheriadis,A.Jacquin.Automatic Face Location Detection and Tracking for Model-Assisted Coding of Video Teleconference Sequences at Low Bit Rates[J].Signal Processing - Image Communication,1995,7(3):231-248.
[58]洪宇,高广珠,余理富,等.一种基于动态背景的运动车辆跟踪算法[J].计算机应用研究,2004,6(5):107-109.
[59]Su Jianbo,Xi Yugeng,Tang shantung.Planar Motion Tracking with an Uncalibrated Robort/Vision System[J].Systems Engineering and Electronics,1998,9(4):45-50.
[60]欧宗瑛,袁野,张艳珍.基于颜色信息足球机器人视觉跟踪算法[J].大连理工大学学报,2000,40(6):729-732.
[61]蒋平,沈世锦,陈辉堂,等.基于图像误差的机器人运动目标自适应跟踪[J].机器人,1997,19(6):431-437.
[62]常红,王涌天等.基于计算机视觉技术的手形手位跟踪方法[J].北京理工大学学报,1999,19(6):739-743.
[63]张莉,吴剑锋,林强.B超心脏序列图像左室短轴轮廓曲线的动态跟踪[J].福州大学学报,2000,28(6):22-25.
[64]胡匡祜,苏万芳,李翊华,等.运动红细胞形变结构的图像自动定量分析的研 究[J].生物物理学报,1994,10(3):387-392.
[65]潘春荣,郑黎明.点模式匹配在羽毛弯度测量中的应用[J].计算机测量与控制,2007,15(2):172-173.
[66]曾英,王国才,李涛.一种新的点模式指纹匹配算法[J].计算机测量与控制,2007,15(7):959-961.
[67]杨红,唐健.一种基于可变限界盒的指纹匹配算法[J].沈阳工业学院学报,2003(12),22(4):9-12.
[68]罗三定,崔振峰,沙莎.一种实时多目标跟踪的新算法[J].计算机测量与控制,2006,14(8):1108-1109.
[69]崔振峰.棒材图像高效识别算法与容错性能研究:[硕士学位论文].长沙:中南大学,2006.