基于单目视觉的水下目标识别与三维定位技术研究
|
摘要
水下光视觉技术作为水下机器人研究的重要内容之一,水下目标识别和三维定位技术是水下机器人探测和作业的基础和关键技术,已经成为水下机器人研究的热点问题之一,受到国内外学者的广泛关注。水下光视觉技术研究对提高水下机器人智能化水平具有重要的研究意义和实用价值。
本文对水下机器人目标识别与三维定位技术中的水下图像预处理、目标物形状特征提取、纹理特征提取、特征融合以及结构光三维定位、系统标定、目标自动识别与单目视觉的三维定位等具体问题进行了相关的研究工作。
在水下图像预处理研究中,针对经典中值滤波算法在脉冲噪声出现概率较大时会使图像产生失真的问题,本文引入自适应中值滤波,通过变换窗口的大小,并且判断窗口内的像素中值及滤波处的像点是否为脉冲噪声,分别进行处理,减小了图像的失真,保护了线段或边缘等细节信息。水下图像极低的对比度使得基于传统的结构特征或一般的灰度特征进行模糊增强难以达到理想效果。针对此问题,本文在变换域内进行模糊增强,基于最大熵原理确定增强阈值,增加背景和目标物的对比度。通过实验对本文提出的预处理方法的有效性进行了验证。
在目标物特征提取的研究中,本文在传统Hu氏不变矩的基础上,增加摄像机镜头径向畸变因子,重新构造新的不变矩,使得目标像素点的灰度值与像素位置得到更好地对应,提高特征向量对目标物的聚类能力：结合统计法和频谱法提取目标物纹理特征,并且将来自目标的形状和纹理特征进行融合,产生比单一特征更精确和完全的判决。设计了基于改进BP算法的神经网络分类器,特征提取和目标识别实验验证了本文方法的有效性。
在水下目标物三维定位的研究中,针对双目或多目立体视觉匹配难的问题,本文提出一种线形激光发射器与水下摄像机相结合的单目视觉三维定位方法。该方法采用几何原理,三维坐标通过参数计算获得而非在线估计,同时本文对水下折射的影响进行了修正,减小了深度信息的失真,定位精度得到提高。在线结构光中心条纹提取技术研究中,针对水下的散折射影响使得光强并非像传统的灰度重心法中一样严格地符合正态分布的问题,本文提出一种基于阈值法和可变方向模板技术相结合的改进算法,提高了线结构光图像的处理速度和光条纹中心的提取准确性。水下目标定位实验验证了本文提出的定位方法以及修正水下折射法方法对于提高目标三维定位精度的有效性。
在摄像机和定位系统的标定研究中,针对传统的马颂德方法中空间正交平移运动难于实现的问题,本文提出一种基于平面正交平移运动的摄像机参数标定方法,并且加入摄像机径向畸变因子,标定精度得到了提高；对于线结构光系统的标定,基于平移变换的思想,以简化标定结构为主要目标,提出一种针对线结构光的单目视觉定位系统结构参数标定方法。水下目标定位实验验证了本文提出的系统标定方法可以提高目标物三维定位的精度。
The underwater optical vision technology is one of the important field of the underwater robotic researching. As the basis and key technologies for underwater robot detecting and operating, the automatic target recognition and three dimensional localization techniques have been one of the hot issues of underwater robot research, attracting more and more attention from scholars at home and abroad. The research on underwater optical vision technology shows important research significance and practical value for improving intelligence level of underwater robot.
Aim at the target recognition and three dimensional techniques, and on the base of pretreatment of underwater images, this paper carries out some specific research works about shape feature extraction, texture feature extraction, feature fusion, three dimensional localization of structured light and system calibration.
In the process of pretreatment of underwater images, aim at the question that the traditional median filter may bring serious distortion to images when the probability of impulse noise is large, this paper introduces adaptive median filter. This method uses the window whose size can change, and judges whether the median pixels in the window and filtering pixels are the impulse noise, then disposes them respectively, which reduces distortion and protects details. The general fuzzy enhancement methods on the base of traditional structure feature and gray feature are inadaptive to underwater images with extremely low contrast and blurry texture. Aim at this problem, this paper brings forward a method to determine the enhancement threshold based on the maximum entropy theory, and carries out fuzzy enhancement in transform domain to increase contrast between background and object. Experimentation validates the pretreatment method brought forward in this paper is effective.
In the research on extracting feature of object, on the base of the traditional Hu moment invariants, the new Hu moment invariants are structured newly in this paper. This method considers radial distortion of camera on the base of original moment invariants, so the gray value and position of pixels can be correspondent batter, which improves the clustering ability of eigenvectors to object; When extract texture feature, the Statistical method based on normalized histogram and spectrum method based on Fourier transform are combined, and then a representation method combined with shape feature and texture feature of the object is presented in this paper, which bring the preciser and more complete judgement than single feature. The target cognition classifier is designed in this paper based on improved BP neural network. Methods presented in the above paper are proved effective according to the feature extraction and target cognition experiments.
In the researching of three dimensional localization for underwater target, aim at the matching in stereo binocular vision is difficult, a three dimensional localization method based on monocular vision is presented in this paper, which combines line shape laser emitter and underwater camera. The three dimensional coordinates are obtained by parameters calculating while not by on-line estimation, and the underwater refraction infection is corrected, which reduces the distortion of depth information and improves the localization precision. In the research of the key technology to extract center fringe of structured light, considering the infection induced by scattering and refraction that make the intensity doesn't accord with normal distribution, which leading to the exact location of fringe center can't be extracted by the traditional gray weighted centroid algorithm, so a improved extraction method is presented in this paper in which threshold method and direction-variable template technology are combined. This method plays the advantages of both the method fully to improve disposal speed and extraction veracity. The locating experiments of underwater target show that the locating method and improvement work presented in this paper is available to improve three dimensional locating precision of the targets.
In the researching of calibrating camera and locating system, aim at the problem that the traditional method brought forward by Ma Songde ignored radial distortion of the camera and the translational motion in three dimensional spaces is difficult to realize, a new method to calibrate camera parameters based on plane translational motion is presented in this paper, and the camera radial distortion factor is considered, which improves the locating precision; For calibrating the structure parameters of structured light system, a calibrating method for monocular vision and structured light locating system is presented in this paper, which takes the translation transformation as the thought and simplifying calibration structure as main purpose to reduce cost. The locating experiments of underwater target show that the system calibration method presented in this paper can improve three dimensional locating precision of the targets availably.
本文对水下机器人目标识别与三维定位技术中的水下图像预处理、目标物形状特征提取、纹理特征提取、特征融合以及结构光三维定位、系统标定、目标自动识别与单目视觉的三维定位等具体问题进行了相关的研究工作。
在水下图像预处理研究中,针对经典中值滤波算法在脉冲噪声出现概率较大时会使图像产生失真的问题,本文引入自适应中值滤波,通过变换窗口的大小,并且判断窗口内的像素中值及滤波处的像点是否为脉冲噪声,分别进行处理,减小了图像的失真,保护了线段或边缘等细节信息。水下图像极低的对比度使得基于传统的结构特征或一般的灰度特征进行模糊增强难以达到理想效果。针对此问题,本文在变换域内进行模糊增强,基于最大熵原理确定增强阈值,增加背景和目标物的对比度。通过实验对本文提出的预处理方法的有效性进行了验证。
在目标物特征提取的研究中,本文在传统Hu氏不变矩的基础上,增加摄像机镜头径向畸变因子,重新构造新的不变矩,使得目标像素点的灰度值与像素位置得到更好地对应,提高特征向量对目标物的聚类能力：结合统计法和频谱法提取目标物纹理特征,并且将来自目标的形状和纹理特征进行融合,产生比单一特征更精确和完全的判决。设计了基于改进BP算法的神经网络分类器,特征提取和目标识别实验验证了本文方法的有效性。
在水下目标物三维定位的研究中,针对双目或多目立体视觉匹配难的问题,本文提出一种线形激光发射器与水下摄像机相结合的单目视觉三维定位方法。该方法采用几何原理,三维坐标通过参数计算获得而非在线估计,同时本文对水下折射的影响进行了修正,减小了深度信息的失真,定位精度得到提高。在线结构光中心条纹提取技术研究中,针对水下的散折射影响使得光强并非像传统的灰度重心法中一样严格地符合正态分布的问题,本文提出一种基于阈值法和可变方向模板技术相结合的改进算法,提高了线结构光图像的处理速度和光条纹中心的提取准确性。水下目标定位实验验证了本文提出的定位方法以及修正水下折射法方法对于提高目标三维定位精度的有效性。
在摄像机和定位系统的标定研究中,针对传统的马颂德方法中空间正交平移运动难于实现的问题,本文提出一种基于平面正交平移运动的摄像机参数标定方法,并且加入摄像机径向畸变因子,标定精度得到了提高；对于线结构光系统的标定,基于平移变换的思想,以简化标定结构为主要目标,提出一种针对线结构光的单目视觉定位系统结构参数标定方法。水下目标定位实验验证了本文提出的系统标定方法可以提高目标物三维定位的精度。
The underwater optical vision technology is one of the important field of the underwater robotic researching. As the basis and key technologies for underwater robot detecting and operating, the automatic target recognition and three dimensional localization techniques have been one of the hot issues of underwater robot research, attracting more and more attention from scholars at home and abroad. The research on underwater optical vision technology shows important research significance and practical value for improving intelligence level of underwater robot.
Aim at the target recognition and three dimensional techniques, and on the base of pretreatment of underwater images, this paper carries out some specific research works about shape feature extraction, texture feature extraction, feature fusion, three dimensional localization of structured light and system calibration.
In the process of pretreatment of underwater images, aim at the question that the traditional median filter may bring serious distortion to images when the probability of impulse noise is large, this paper introduces adaptive median filter. This method uses the window whose size can change, and judges whether the median pixels in the window and filtering pixels are the impulse noise, then disposes them respectively, which reduces distortion and protects details. The general fuzzy enhancement methods on the base of traditional structure feature and gray feature are inadaptive to underwater images with extremely low contrast and blurry texture. Aim at this problem, this paper brings forward a method to determine the enhancement threshold based on the maximum entropy theory, and carries out fuzzy enhancement in transform domain to increase contrast between background and object. Experimentation validates the pretreatment method brought forward in this paper is effective.
In the research on extracting feature of object, on the base of the traditional Hu moment invariants, the new Hu moment invariants are structured newly in this paper. This method considers radial distortion of camera on the base of original moment invariants, so the gray value and position of pixels can be correspondent batter, which improves the clustering ability of eigenvectors to object; When extract texture feature, the Statistical method based on normalized histogram and spectrum method based on Fourier transform are combined, and then a representation method combined with shape feature and texture feature of the object is presented in this paper, which bring the preciser and more complete judgement than single feature. The target cognition classifier is designed in this paper based on improved BP neural network. Methods presented in the above paper are proved effective according to the feature extraction and target cognition experiments.
In the researching of three dimensional localization for underwater target, aim at the matching in stereo binocular vision is difficult, a three dimensional localization method based on monocular vision is presented in this paper, which combines line shape laser emitter and underwater camera. The three dimensional coordinates are obtained by parameters calculating while not by on-line estimation, and the underwater refraction infection is corrected, which reduces the distortion of depth information and improves the localization precision. In the research of the key technology to extract center fringe of structured light, considering the infection induced by scattering and refraction that make the intensity doesn't accord with normal distribution, which leading to the exact location of fringe center can't be extracted by the traditional gray weighted centroid algorithm, so a improved extraction method is presented in this paper in which threshold method and direction-variable template technology are combined. This method plays the advantages of both the method fully to improve disposal speed and extraction veracity. The locating experiments of underwater target show that the locating method and improvement work presented in this paper is available to improve three dimensional locating precision of the targets.
In the researching of calibrating camera and locating system, aim at the problem that the traditional method brought forward by Ma Songde ignored radial distortion of the camera and the translational motion in three dimensional spaces is difficult to realize, a new method to calibrate camera parameters based on plane translational motion is presented in this paper, and the camera radial distortion factor is considered, which improves the locating precision; For calibrating the structure parameters of structured light system, a calibrating method for monocular vision and structured light locating system is presented in this paper, which takes the translation transformation as the thought and simplifying calibration structure as main purpose to reduce cost. The locating experiments of underwater target show that the system calibration method presented in this paper can improve three dimensional locating precision of the targets availably.
引文
[1]杨理践,于振华,高松巍.水下超声波测距技术的研究[J].可靠性分析.2008,3：48-64页
[2]赵伟博.基于线激光扫描的三维测距系统[D].[硕士学位论文].杭州：浙江大学.2008：5-7页
[3]C.L.Foresti, S.Gentili. A vision based system for object detection in underwater images[J]. International Journal of Pattern Recognition and Artificial Intelligence.2006,14(2):167-188P
[4]Zwe-Lee Gaing. Discrete Particle Swarm Optimization Algorithm for Unit Commitment[C]. IEEE Power Engineering Society General Meeting. Ontario, Canada,2003(1):418-424P
[5]Liu Bo. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos, So'tons&Fractals.2005,25(5):1261-1271P
[6]Amaury Negre, Cedric Pradalier. Robust Vision-based Underwater Target Identification and Homing Using Self-Similar Landmarks[J]. Field and Service Robotics.2008,42:51-60P
[7]Vlachos I K, Serials G D. Fuzzy Reasoning Scheme for Edge Detection Using Local Edge Information Based on Renyi's Entropy[J]. Signal Processing and Its Application.2003:543-549P
[8]Wirth D, Lyon J, Nikitenko D. A Fuzzy Approach to Segmenting the Breast Region in Mammograms. Fuzzy Information Processing. NAFIPS'04,2004:469-474P
[9]冯占国,徐玉如.基于不变性特征的水下目标特征提取[J].哈尔滨工程大学学报.2007,28(12)：1343-1346页
[10]史廷彦,赵书斌.基于不变矩和角点特征的目标识别[J].指挥控制与仿真.2008,30(2)：32-34页
[11]韩云生,刘国栋.一种自适应颜色特征的目标识别与跟踪法[J].江南大学学报.2009,8(2)：164-168页
[12]Sookhanaphibarn Kingkarn, Lursinsap Chidchanok. A New Feature Extractor Invariant to Intensity, Rotation and Scaling of Color Images[J]. Information Sciences.2006,176:2097-2119P
[13]Chenchen Liu, Zhimeng Zhang, Enfang Sang. A Noval Acoustical Vision System Design for Automated Underwater Vehicles[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation. June 25-27,2008, Chongqing, China:7438-7443P
[14]Amaury Negre. Rotation-Invariant Texture Classification Using Feature Distributions[J]. Pattern Recognition.2008,33(4):43-52P
[15]K. Rajesh et al. Performance Analysis of Textural Features for Characterization and Classification of SAR Images [J]. International Journal of Remote Sensing.2008,22(8):1555-1569P
[16]Damaryam.G. The Consensus Operator for Combining Beliefs[J]. Artificial Intelligence Journal.2005,142(1-2):157-170P
[17]Gan Du, Shouhong Zhang. Estimation of Three-Dimensional Motion Parameters in Interferometric ISAR Imaging[C]. IEEE Transaction on Geoscience and Remote Sensing.2004,42(2):292-297P
[18]于秀芬,段海宾,龚华军.移动机器人视觉定位方法的研究和实现[J].数据采集与处理.2004,19(4)：433-437页
[19]S.L.Iu.K.Whon. Estimation of 3D Motion and Structure Based on Temporally-oriented Approach with Method of Regression[C]. IEEE of Workshop on Visual Motion.1989:273-281P
[20]郭磊,徐春友等.基于单目视觉的实时测距方法研究[J].中国图象图形学报.2006,11(1)：74-81页
[21]Fernandez.E.J, Prieto.P.M, Artal.P. Binocular Adaptive Optics Visual Simulator[J]. Optics Letters.2009,34(17):2628-2630P
[22]Clark F.Olson, Hahib Abi-Rached, Jonathan P.Hendrich. Wide-Baseline Stero Vision for Mars Rovers[C]. Proceedings of the 2003 IEEE. Conference on Intelligent Robots and Systems.2003:1032-1038P
[23]肖心远.视觉引导下的机器人跟踪复杂焊缝的研究[J].焊接技术.2006,30(5)：125-129页
[24]王忠立.基于立体视觉的空间球体快速定位方法[J].北京理工大学学报.2007,26(11)：974-977页
[25]王宗义.线结构光视觉传感器与水下三维探测[D].[博士学位论文].哈尔滨：哈尔滨工程大学.2005,15-17页
[26]Radovan Gospavic, Milesa Sreckovic, Viktor Popoc.3D Modeling of Material Heating with the Laser Beam for Cylindrical Geometry [J]. Mathematical and Computer Modeling.2006,43:620-631P
[27]Yan Zhou, Quanhua, Weidong Jin. A Fast Adaptive Switching Median Filter Based on Measure Integral[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation. Chengdu, China,2008: 6760-6763P
[28]Hoyos S, Li B, Bacca J, et al. Weighted Median Filters Admitting Complex-valued Weighted and Their Optimization[J]. IEEE Trans. Signal Processing,2004,52(10):2776-2787P
[29]贺恩华,朱利民.自适应中值滤波器及其应用[J].振动、测试与诊断.2006,1：70-72页
[30]Yo-Ping Huang, Tsun-Wei Chang. A Fuzzy Inference Model for Image Segmentation[J]. The 12th IEEE International Conference on Fuzzy Systems. May 25-28,2003:972-977P
[31]Altera Inc. Cyclone II Device Handbook. http://www.altera.com/literature/hb/cys2/cyc2 cii5vl 01.pdf.2006
[32]Altera Inc. Quartus Ⅱ Version 6.0 Handbook. http://www.altera.com/literature/hb/qts/qts qii5v2 01.pdf.2006
[33]王随平,孙淑绒,张艳存.基于相对熵的水下图像模糊增强与边缘检测算法[J].现代电子技术.2008,4：142-144页
[34]杨宏辉,孙进才‘.基于支持向量机集成的水下目标自动识别系统[J].测控技术.2006,25(12)：14-16页
[35]王菲,曾庆军,黄国建,李洪瑞.基于遗传BP算法的神经网络目标分类器的研究[J].华东船舶工业学院学报.2001,15(2)：43-47页
[36]Zwe-Lee Gaing. Discrate particle swarm optimization algorithm for unit commitment[C]. IEEE Power Engineering Society General Meeting. Ontario, Canada,2003(1):418-424P
[37]Liu Bo, et al. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos, Solitons & Fractals,2005,25(5):1261-1271P
[38]詹艳梅,曾向阳.基于粗糙集理论的目标特征选择方法[J].自然科学进展.2004,14(12)：1483-1487页
[39]赵妮,梁峰.基于BPSO的水下目标特征选择方法[J].计算机仿真.2008,25(1)：196-199页
[40]王耀明.图像的矩函数-原理、算法及应用.第一版[M].上海华东理工大学出版社.2002：3页
[41]Liu J, Zhang T X. Fast algorithm for generation of moment invariants[J]. Pattern Recognition.2004,37(8):1785-1786P
[42]Shao Yuan, Celenk M. High-order spectra (HOS) invariants for shape recognition[J]. Pattern Recognition.2001,34(11):2097-2113P
[43]Chen Y F, Zhang M D. Local moment invariant analysis[C]. Proceedings of the Conference on Computer Graphics, Imaging and Vision:New Trends 2005. Piscataway:Institute of Electrical and Electronics Engineers Computer Society,2005:137-140P
[44]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电子学报.2006,34(1)：155-158页
[45]D.A.Clausi and B.Yue. Comparing Cooccurrence probabilities and Markov Random Fields for Texture Analysis of SAR Sea Ice Imagery[C]. IEEE Transactions on Geoscience and Remote Sensing.2004,42(1): 215-225P
[46]Puig Domenec, Garcia Miguel Angel. Automatic Texture Feature Selection for Image Pixel Classification[J]. Pattern Recognition.2006,39: 1996-2009P
[47]Sengur A. Wavelet Transform and Adaptive Neuro-fuzzy Inference System for Color Texture Classification[J]. Expert System with Applications.2008,34:2120-2128P
[48]张志龙,鲁新平,沈振康.基于局部沃尔什变换的纹理特征提取方法研究[J].信号处理.2005,21(6)：589-596页
[49]Clausi D A, Deng H. Design-based Texture Feature Fusion Using Garbor Filters and Cooccurrence Probabilities[C]. IEEE Transactions on Image Processing.2005,14(7):925-936P
[50]Ville Kyrki, Joni-Kristian, Kamarainen etal. Simple Gabor Feature Space for Invariant Object Recognition[J]. Pattern Recognition Letters.2004, 25:311-318P
[51]郭禾,李寒,王宇新.机器人三维定位系统中关键技术的研究[J].系统仿真学报.2006,18(1)：99-102页
[52]刘晶晶.基于双目立体视觉的三维定位技术研究[D].华中科技大学硕士学位论文.2007
[53]WenChung Chang. Binocular Vision-based 3-D Trajectory Following for Autonomous Robotic Manipulation[J]. Robotica.2007,25(5):615-626P
[54]杨杰,张铭钧,徐建安.移动机器人的视觉跟踪方法的研究[J].第 六届全球智能控制与自动化大会论文集.Piscataway:Institute of Electrical and Electronics Engineers Inc,2006:9017-9021页(EI: 071510544264 ISTP:000241773209240)
[55]Sornakumar, T, Paramasivam, C. Computer Vision Based Positional Error Compensation of an Industrial Robot Using Linear Regression Analysis. International Journal of Manufacturing Research. v3, n2,2008: 252-264P
[56]Sjoerd van der Zwaan, Jose Santos-Victor. Real-time Vision-based Station Keeping for Underwater Robots[C]. OCEANS'2001 MTS/IEEE Conf and Exhibition. Piscataway.2001:1058-1065P
[57]Zhengyou ZHANG. A Flexible New Technique for Camera Calibration[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,22(11):1330-1334P
[58]Ricolfe-Viala.C, Sanchez-Salmeron.A.-J. Improved Camera Calibration Method Based on A Two-dimensional Template[J]. Pattern Recongnition and Image Analysis.2007:420-427P
[59]英向华.全向摄像机标定技术研究[D].中国科学院博士论文.2004.
[60]Wong K K, Mendonca P R S, Cipolla R. Camera Calibration from Surfaces of Revolution[C]. IEEE Transactions on PAMI.2003,25(2): 147-161P
[61]陈爱华,高诚辉,何炳蔚.计算机视觉中的摄像机标定方法[J].中国工程机械学报.2006,4(4)：498-504页
[62]Hartley R. Self-calibration of Stationary Cameras[J]. International Journal of Computer Vision.1997,22(1):5-23P
[63]徐静.基于非线性模型的摄像机标定技术研究[J].现代电子技术.2008,12：159-162页
[64]Tsai R Y. An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision[C]. In:Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Miami Beach, FL.1986:364-374P
[65]周富强,张广军,江洁.线结构光视觉传感器的现场标定方法[J].机械工程学报.2004,40(6)：169-173页
[66]魏振忠.基于机器视觉的在线柔性三坐标测量系统研究[D].北京：北京航空航天大学博士学位论文.2003,4页
[67]M.A.G. Izquierdo, M.T. Sanchez, A.Ibanez, L.G.Ullate. Sub-pixel Measurement of 3D Surfaces by Laser Scanning[J]. Sensors and Actuators, A:Physical.1999,76(1-3):1-8P
[68]张勇斌,卢荣胜,刘志健,吴彰良.线结构光视觉测量系统的标定方法[J].传感器世界.2003,8：10-13页
[69]Wang Guoyu, Zheng Bing, Li Xin, Houkes Zweitze, Regtien Paul P.L, Modelling and Calibration of the Laser Beam-scanning Triangulation Measurement System[J]. Robotics and Autonomous System.2002,40(4): 267-277P
[70]段发阶,刘凤梅,叶声华.一种新型线结构光传感器参数标定方法[J].仪器仪表学报.2000,21(1)：108-110页
[71]Wallace, A.M., Zhang, G., Galllaher, Y. Scan Calibration or Compensation in a Depth Imaging System[J]. Pattern Recognition Letters.2001,19(17):605-612P
[72]A. Dipanda, S.Woo, F.Marzani, J.M.Bilbault.3-D Shape Reconstruction in an Active Stereo Vision System Using Genetic Algorithms [J]. Pattern, Recognition.2003,36(9):2143-2159P
[73]张广军,魏振忠,孙志武,李鑫.基于BP神经网络的结构光三维视觉检测方法研究[J].仪器仪表学报.2002,23(1)：31-35页
[2]赵伟博.基于线激光扫描的三维测距系统[D].[硕士学位论文].杭州：浙江大学.2008：5-7页
[3]C.L.Foresti, S.Gentili. A vision based system for object detection in underwater images[J]. International Journal of Pattern Recognition and Artificial Intelligence.2006,14(2):167-188P
[4]Zwe-Lee Gaing. Discrete Particle Swarm Optimization Algorithm for Unit Commitment[C]. IEEE Power Engineering Society General Meeting. Ontario, Canada,2003(1):418-424P
[5]Liu Bo. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos, So'tons&Fractals.2005,25(5):1261-1271P
[6]Amaury Negre, Cedric Pradalier. Robust Vision-based Underwater Target Identification and Homing Using Self-Similar Landmarks[J]. Field and Service Robotics.2008,42:51-60P
[7]Vlachos I K, Serials G D. Fuzzy Reasoning Scheme for Edge Detection Using Local Edge Information Based on Renyi's Entropy[J]. Signal Processing and Its Application.2003:543-549P
[8]Wirth D, Lyon J, Nikitenko D. A Fuzzy Approach to Segmenting the Breast Region in Mammograms. Fuzzy Information Processing. NAFIPS'04,2004:469-474P
[9]冯占国,徐玉如.基于不变性特征的水下目标特征提取[J].哈尔滨工程大学学报.2007,28(12)：1343-1346页
[10]史廷彦,赵书斌.基于不变矩和角点特征的目标识别[J].指挥控制与仿真.2008,30(2)：32-34页
[11]韩云生,刘国栋.一种自适应颜色特征的目标识别与跟踪法[J].江南大学学报.2009,8(2)：164-168页
[12]Sookhanaphibarn Kingkarn, Lursinsap Chidchanok. A New Feature Extractor Invariant to Intensity, Rotation and Scaling of Color Images[J]. Information Sciences.2006,176:2097-2119P
[13]Chenchen Liu, Zhimeng Zhang, Enfang Sang. A Noval Acoustical Vision System Design for Automated Underwater Vehicles[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation. June 25-27,2008, Chongqing, China:7438-7443P
[14]Amaury Negre. Rotation-Invariant Texture Classification Using Feature Distributions[J]. Pattern Recognition.2008,33(4):43-52P
[15]K. Rajesh et al. Performance Analysis of Textural Features for Characterization and Classification of SAR Images [J]. International Journal of Remote Sensing.2008,22(8):1555-1569P
[16]Damaryam.G. The Consensus Operator for Combining Beliefs[J]. Artificial Intelligence Journal.2005,142(1-2):157-170P
[17]Gan Du, Shouhong Zhang. Estimation of Three-Dimensional Motion Parameters in Interferometric ISAR Imaging[C]. IEEE Transaction on Geoscience and Remote Sensing.2004,42(2):292-297P
[18]于秀芬,段海宾,龚华军.移动机器人视觉定位方法的研究和实现[J].数据采集与处理.2004,19(4)：433-437页
[19]S.L.Iu.K.Whon. Estimation of 3D Motion and Structure Based on Temporally-oriented Approach with Method of Regression[C]. IEEE of Workshop on Visual Motion.1989:273-281P
[20]郭磊,徐春友等.基于单目视觉的实时测距方法研究[J].中国图象图形学报.2006,11(1)：74-81页
[21]Fernandez.E.J, Prieto.P.M, Artal.P. Binocular Adaptive Optics Visual Simulator[J]. Optics Letters.2009,34(17):2628-2630P
[22]Clark F.Olson, Hahib Abi-Rached, Jonathan P.Hendrich. Wide-Baseline Stero Vision for Mars Rovers[C]. Proceedings of the 2003 IEEE. Conference on Intelligent Robots and Systems.2003:1032-1038P
[23]肖心远.视觉引导下的机器人跟踪复杂焊缝的研究[J].焊接技术.2006,30(5)：125-129页
[24]王忠立.基于立体视觉的空间球体快速定位方法[J].北京理工大学学报.2007,26(11)：974-977页
[25]王宗义.线结构光视觉传感器与水下三维探测[D].[博士学位论文].哈尔滨：哈尔滨工程大学.2005,15-17页
[26]Radovan Gospavic, Milesa Sreckovic, Viktor Popoc.3D Modeling of Material Heating with the Laser Beam for Cylindrical Geometry [J]. Mathematical and Computer Modeling.2006,43:620-631P
[27]Yan Zhou, Quanhua, Weidong Jin. A Fast Adaptive Switching Median Filter Based on Measure Integral[C]. Proceedings of the 7th World Congress on Intelligent Control and Automation. Chengdu, China,2008: 6760-6763P
[28]Hoyos S, Li B, Bacca J, et al. Weighted Median Filters Admitting Complex-valued Weighted and Their Optimization[J]. IEEE Trans. Signal Processing,2004,52(10):2776-2787P
[29]贺恩华,朱利民.自适应中值滤波器及其应用[J].振动、测试与诊断.2006,1：70-72页
[30]Yo-Ping Huang, Tsun-Wei Chang. A Fuzzy Inference Model for Image Segmentation[J]. The 12th IEEE International Conference on Fuzzy Systems. May 25-28,2003:972-977P
[31]Altera Inc. Cyclone II Device Handbook. http://www.altera.com/literature/hb/cys2/cyc2 cii5vl 01.pdf.2006
[32]Altera Inc. Quartus Ⅱ Version 6.0 Handbook. http://www.altera.com/literature/hb/qts/qts qii5v2 01.pdf.2006
[33]王随平,孙淑绒,张艳存.基于相对熵的水下图像模糊增强与边缘检测算法[J].现代电子技术.2008,4：142-144页
[34]杨宏辉,孙进才‘.基于支持向量机集成的水下目标自动识别系统[J].测控技术.2006,25(12)：14-16页
[35]王菲,曾庆军,黄国建,李洪瑞.基于遗传BP算法的神经网络目标分类器的研究[J].华东船舶工业学院学报.2001,15(2)：43-47页
[36]Zwe-Lee Gaing. Discrate particle swarm optimization algorithm for unit commitment[C]. IEEE Power Engineering Society General Meeting. Ontario, Canada,2003(1):418-424P
[37]Liu Bo, et al. Improved Particle Swarm Optimization Combined with Chaos[J]. Chaos, Solitons & Fractals,2005,25(5):1261-1271P
[38]詹艳梅,曾向阳.基于粗糙集理论的目标特征选择方法[J].自然科学进展.2004,14(12)：1483-1487页
[39]赵妮,梁峰.基于BPSO的水下目标特征选择方法[J].计算机仿真.2008,25(1)：196-199页
[40]王耀明.图像的矩函数-原理、算法及应用.第一版[M].上海华东理工大学出版社.2002：3页
[41]Liu J, Zhang T X. Fast algorithm for generation of moment invariants[J]. Pattern Recognition.2004,37(8):1785-1786P
[42]Shao Yuan, Celenk M. High-order spectra (HOS) invariants for shape recognition[J]. Pattern Recognition.2001,34(11):2097-2113P
[43]Chen Y F, Zhang M D. Local moment invariant analysis[C]. Proceedings of the Conference on Computer Graphics, Imaging and Vision:New Trends 2005. Piscataway:Institute of Electrical and Electronics Engineers Computer Society,2005:137-140P
[44]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电子学报.2006,34(1)：155-158页
[45]D.A.Clausi and B.Yue. Comparing Cooccurrence probabilities and Markov Random Fields for Texture Analysis of SAR Sea Ice Imagery[C]. IEEE Transactions on Geoscience and Remote Sensing.2004,42(1): 215-225P
[46]Puig Domenec, Garcia Miguel Angel. Automatic Texture Feature Selection for Image Pixel Classification[J]. Pattern Recognition.2006,39: 1996-2009P
[47]Sengur A. Wavelet Transform and Adaptive Neuro-fuzzy Inference System for Color Texture Classification[J]. Expert System with Applications.2008,34:2120-2128P
[48]张志龙,鲁新平,沈振康.基于局部沃尔什变换的纹理特征提取方法研究[J].信号处理.2005,21(6)：589-596页
[49]Clausi D A, Deng H. Design-based Texture Feature Fusion Using Garbor Filters and Cooccurrence Probabilities[C]. IEEE Transactions on Image Processing.2005,14(7):925-936P
[50]Ville Kyrki, Joni-Kristian, Kamarainen etal. Simple Gabor Feature Space for Invariant Object Recognition[J]. Pattern Recognition Letters.2004, 25:311-318P
[51]郭禾,李寒,王宇新.机器人三维定位系统中关键技术的研究[J].系统仿真学报.2006,18(1)：99-102页
[52]刘晶晶.基于双目立体视觉的三维定位技术研究[D].华中科技大学硕士学位论文.2007
[53]WenChung Chang. Binocular Vision-based 3-D Trajectory Following for Autonomous Robotic Manipulation[J]. Robotica.2007,25(5):615-626P
[54]杨杰,张铭钧,徐建安.移动机器人的视觉跟踪方法的研究[J].第 六届全球智能控制与自动化大会论文集.Piscataway:Institute of Electrical and Electronics Engineers Inc,2006:9017-9021页(EI: 071510544264 ISTP:000241773209240)
[55]Sornakumar, T, Paramasivam, C. Computer Vision Based Positional Error Compensation of an Industrial Robot Using Linear Regression Analysis. International Journal of Manufacturing Research. v3, n2,2008: 252-264P
[56]Sjoerd van der Zwaan, Jose Santos-Victor. Real-time Vision-based Station Keeping for Underwater Robots[C]. OCEANS'2001 MTS/IEEE Conf and Exhibition. Piscataway.2001:1058-1065P
[57]Zhengyou ZHANG. A Flexible New Technique for Camera Calibration[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,22(11):1330-1334P
[58]Ricolfe-Viala.C, Sanchez-Salmeron.A.-J. Improved Camera Calibration Method Based on A Two-dimensional Template[J]. Pattern Recongnition and Image Analysis.2007:420-427P
[59]英向华.全向摄像机标定技术研究[D].中国科学院博士论文.2004.
[60]Wong K K, Mendonca P R S, Cipolla R. Camera Calibration from Surfaces of Revolution[C]. IEEE Transactions on PAMI.2003,25(2): 147-161P
[61]陈爱华,高诚辉,何炳蔚.计算机视觉中的摄像机标定方法[J].中国工程机械学报.2006,4(4)：498-504页
[62]Hartley R. Self-calibration of Stationary Cameras[J]. International Journal of Computer Vision.1997,22(1):5-23P
[63]徐静.基于非线性模型的摄像机标定技术研究[J].现代电子技术.2008,12：159-162页
[64]Tsai R Y. An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision[C]. In:Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Miami Beach, FL.1986:364-374P
[65]周富强,张广军,江洁.线结构光视觉传感器的现场标定方法[J].机械工程学报.2004,40(6)：169-173页
[66]魏振忠.基于机器视觉的在线柔性三坐标测量系统研究[D].北京：北京航空航天大学博士学位论文.2003,4页
[67]M.A.G. Izquierdo, M.T. Sanchez, A.Ibanez, L.G.Ullate. Sub-pixel Measurement of 3D Surfaces by Laser Scanning[J]. Sensors and Actuators, A:Physical.1999,76(1-3):1-8P
[68]张勇斌,卢荣胜,刘志健,吴彰良.线结构光视觉测量系统的标定方法[J].传感器世界.2003,8：10-13页
[69]Wang Guoyu, Zheng Bing, Li Xin, Houkes Zweitze, Regtien Paul P.L, Modelling and Calibration of the Laser Beam-scanning Triangulation Measurement System[J]. Robotics and Autonomous System.2002,40(4): 267-277P
[70]段发阶,刘凤梅,叶声华.一种新型线结构光传感器参数标定方法[J].仪器仪表学报.2000,21(1)：108-110页
[71]Wallace, A.M., Zhang, G., Galllaher, Y. Scan Calibration or Compensation in a Depth Imaging System[J]. Pattern Recognition Letters.2001,19(17):605-612P
[72]A. Dipanda, S.Woo, F.Marzani, J.M.Bilbault.3-D Shape Reconstruction in an Active Stereo Vision System Using Genetic Algorithms [J]. Pattern, Recognition.2003,36(9):2143-2159P
[73]张广军,魏振忠,孙志武,李鑫.基于BP神经网络的结构光三维视觉检测方法研究[J].仪器仪表学报.2002,23(1)：31-35页