越野机器人运行环境中的障碍物检测方法研究
|
摘要
障碍物检测是影响自主车辆在越野环境下安全运行的主要难题之一。本文对越野运行中存在的两种主要障碍形式—独立障碍物和斜坡类障碍物的视觉检测方法进行了研究。
双目立体视觉技术是检测独立障碍物的主要方法。立体匹配是决定该技术能否实现的关键环节。论文着重对立体匹配进行了研究。传统的区域匹配算法以单一灰度信息为匹配特征,无法满足野外环境对算法的较高要求。提出将颜色信息加入区域匹配特征中。根据提取颜色信息方式的不同,本文研究了RGB、HSI、L*a*b*三种颜色模型。并借鉴视网膜内颜色细胞的拮抗原理对L*a*b*颜色模型进行了简化与改进,称为改进的L*a*b*颜色模型。该模型具有二维色度、一维亮度的简化形式,分别反映了物体材质和表面朝向信息。本文通过实验对比分析了含有颜色与灰度双重信息的匹配算法与灰度匹配算法的环境适应性、稳定性、实时性以及受窗口尺寸变化的影响等多方面性能。结果表明,含有颜色与灰度双重信息匹配算法的抗噪性得到增强,匹配效果优于基于灰度或颜色单一特征的匹配算法;改进的L*a*b*颜色模型具有良好的微小色差辨别能力,在图像平滑区的匹配正确度明显高于其它两种颜色模型。
由于斜坡类障碍表面常覆有密集杂乱的随机纹理,纹理与纹理之间相互交错,会在双目图像中产生遮挡区域,从而造成大量误匹配。本文对单目视觉中可用于表面朝向识别的方法进行了研究,提出利用随机纹理的统计特性来分析斜坡类危险地形的朝向信息。并通过实验验证了该方法的有效性。
加入颜色信息后,匹配算法的计算复杂度与含有灰度单一信息的匹配算法相比有所增加。针对该问题,本文选取FPGA来完成硬件加速。设计了串并转换机制,有效地降低了算法计算复杂度。论文以FPGA Stratix系列EP1S30为目标器件,在Quartus平台上进行了逻辑功能和时序仿真,对比分析了改进L*a*b*算法和RGB算法的实时实现性能。仿真结果表明,改进L*a*b*算法的时间复杂度为RGB算法的1.1倍,属同阶复杂度。
Recently,USA had held competitions about ALV navigation in complex environment many times. The purposes of these were to check the ability of ALV’s environment perception. Cross-country environment has high complexity、many kinds of obstacles and coarseness and bumpiness of the earth surface. All of these cause great difficulties for ALV’s safe running. So it is a very challenging research problem for rough terrain perception. For this purpose, ALV always installs different sensors such as CCD、LADAR、sonar, etc. Vision sensors are important“apparatus”for environment perception and obstacle detection, which have the same function as our eyes. This thesis studies techniques of obstacle detection based on vision sensors. The obstacles which were researched include heave and slope. The main contents of this paper are introduced below in detail:
1. Two kinds of methods about the receiving of obstacle’s 3-D information based on vision sensors are analyzed from arithmetic theory, including stereo vision and monocular vision. In the stereo vision part, we analyzed and compared different kinds of stereo matching algorithms. And in the monocular vision part, applications、merits and shortcomings of monocular vision methods are summed up. From the analysis, we know that the feature matching has good anti-jamming performance. But it can only get sparse disparity and the feature distilling and orientation are instability in complex environment. The area matching can get compact disparity and has high orientation precision. It is fit for off-road. In the methods of computing slants of surfaces based on monocular vision, shading and photometric stereo suffer the effect of lamp intensities and are fit for lamps that can be controlled. The texture analysis computes slant by changes of surface texture structure in the perspective process. It needs not estimate directions of the illumination and apples to natural lamp condition.
2. Binocular stereo vision is the primary method for heave obstacle detection. Stereo matching is the key tache of this method. So this paper stress researches on stereo matching. Single grey correlative matching algorithm can not satisfy requires of robustness .So the method of adding color in similarity matching feature is proposed. This paper had studied RGB、HSI and L*a*b* color model. Also we improve the L*a*b* color model combining the opponent characteristic of color cells in the retina. In this paper, we compare and analyze the performances of improved L*a*b* color model、RGB color model、HSI color model and grey correlative algorithms from many aspects, including environment adaptability、stability、real-time and the influence of matching window size. The experimental results show that performances of algorithms including grey and color(improved L*a*b* color model、HSI color model and RGB color model) exceed single grey correlative or color matching algorithms. Grey and color supplement each other and can’t lack either. Improved L*a*b* algorithm has better matching performanc- es than other algorithms in smooth areas of the image because of its good distinguishing ability in the tiny color difference area.
3. Slope is also a kind of obstacle on cross-country environment. The surfaces of them often cover random textures that are dense and littery, which make against stereo matching. Reference to the form of human visual understanding of the natural environment, we propose computing the slant of slope using textures analysis of the monocular vision. Aiming at difficult of random textures analysis, radial competition method is presented for extracting texture elements which can reflect the size of texture elements and barycenter distributions of the same size texture are received by the statistic method. Based on this, we fit the tilt using Agglomerative Nesting Clustering and Linear method and compute the gradients using continental distance with varying weight. In the last, tilt computing experiment、slant and gradient calibration and algorithm applicability analysis are carried on. Experiment results show that the method can compute the tilt and slant of the surface effectively and the computing error is close to the estimate error of human vision. Furthermore, the method is little affected by gray scale.
4. Although the matching performance of color model algorithms exceed grey algorithm, the computing complexity of color model algorithms are higher than grey algorithm because of more similarity measures. For this problem, hardware accelerating system is designed using FPGA which has high ability of data parallel processing. In this paper, CMOS color image sensors HV7131B are used for image collection and Stratix FPGA EP1S30 is used for core processing module of the whole matching. A ping-pong 2-cache system is designed according to the transmission of HV7131B and the matching efficiency is improved in this way. In the phase of algorithm implementation, we adopt the system that matching in row unit and design 3-class gliding structure which can mitigate the time stress effectively. In this paper, we mostly design the accelerating system for the tache of the original matching cost computing using Series and Parallel turn System and Box filter technology. Also the real-time performance of improved L*a*b* and RGB algorithms are analyzed and compared according to the logical function and time simulation in Quartus. The simulation results show that the time complexity of improved L*a*b* is 1.1times higher than RGB algorithm.
双目立体视觉技术是检测独立障碍物的主要方法。立体匹配是决定该技术能否实现的关键环节。论文着重对立体匹配进行了研究。传统的区域匹配算法以单一灰度信息为匹配特征,无法满足野外环境对算法的较高要求。提出将颜色信息加入区域匹配特征中。根据提取颜色信息方式的不同,本文研究了RGB、HSI、L*a*b*三种颜色模型。并借鉴视网膜内颜色细胞的拮抗原理对L*a*b*颜色模型进行了简化与改进,称为改进的L*a*b*颜色模型。该模型具有二维色度、一维亮度的简化形式,分别反映了物体材质和表面朝向信息。本文通过实验对比分析了含有颜色与灰度双重信息的匹配算法与灰度匹配算法的环境适应性、稳定性、实时性以及受窗口尺寸变化的影响等多方面性能。结果表明,含有颜色与灰度双重信息匹配算法的抗噪性得到增强,匹配效果优于基于灰度或颜色单一特征的匹配算法;改进的L*a*b*颜色模型具有良好的微小色差辨别能力,在图像平滑区的匹配正确度明显高于其它两种颜色模型。
由于斜坡类障碍表面常覆有密集杂乱的随机纹理,纹理与纹理之间相互交错,会在双目图像中产生遮挡区域,从而造成大量误匹配。本文对单目视觉中可用于表面朝向识别的方法进行了研究,提出利用随机纹理的统计特性来分析斜坡类危险地形的朝向信息。并通过实验验证了该方法的有效性。
加入颜色信息后,匹配算法的计算复杂度与含有灰度单一信息的匹配算法相比有所增加。针对该问题,本文选取FPGA来完成硬件加速。设计了串并转换机制,有效地降低了算法计算复杂度。论文以FPGA Stratix系列EP1S30为目标器件,在Quartus平台上进行了逻辑功能和时序仿真,对比分析了改进L*a*b*算法和RGB算法的实时实现性能。仿真结果表明,改进L*a*b*算法的时间复杂度为RGB算法的1.1倍,属同阶复杂度。
Recently,USA had held competitions about ALV navigation in complex environment many times. The purposes of these were to check the ability of ALV’s environment perception. Cross-country environment has high complexity、many kinds of obstacles and coarseness and bumpiness of the earth surface. All of these cause great difficulties for ALV’s safe running. So it is a very challenging research problem for rough terrain perception. For this purpose, ALV always installs different sensors such as CCD、LADAR、sonar, etc. Vision sensors are important“apparatus”for environment perception and obstacle detection, which have the same function as our eyes. This thesis studies techniques of obstacle detection based on vision sensors. The obstacles which were researched include heave and slope. The main contents of this paper are introduced below in detail:
1. Two kinds of methods about the receiving of obstacle’s 3-D information based on vision sensors are analyzed from arithmetic theory, including stereo vision and monocular vision. In the stereo vision part, we analyzed and compared different kinds of stereo matching algorithms. And in the monocular vision part, applications、merits and shortcomings of monocular vision methods are summed up. From the analysis, we know that the feature matching has good anti-jamming performance. But it can only get sparse disparity and the feature distilling and orientation are instability in complex environment. The area matching can get compact disparity and has high orientation precision. It is fit for off-road. In the methods of computing slants of surfaces based on monocular vision, shading and photometric stereo suffer the effect of lamp intensities and are fit for lamps that can be controlled. The texture analysis computes slant by changes of surface texture structure in the perspective process. It needs not estimate directions of the illumination and apples to natural lamp condition.
2. Binocular stereo vision is the primary method for heave obstacle detection. Stereo matching is the key tache of this method. So this paper stress researches on stereo matching. Single grey correlative matching algorithm can not satisfy requires of robustness .So the method of adding color in similarity matching feature is proposed. This paper had studied RGB、HSI and L*a*b* color model. Also we improve the L*a*b* color model combining the opponent characteristic of color cells in the retina. In this paper, we compare and analyze the performances of improved L*a*b* color model、RGB color model、HSI color model and grey correlative algorithms from many aspects, including environment adaptability、stability、real-time and the influence of matching window size. The experimental results show that performances of algorithms including grey and color(improved L*a*b* color model、HSI color model and RGB color model) exceed single grey correlative or color matching algorithms. Grey and color supplement each other and can’t lack either. Improved L*a*b* algorithm has better matching performanc- es than other algorithms in smooth areas of the image because of its good distinguishing ability in the tiny color difference area.
3. Slope is also a kind of obstacle on cross-country environment. The surfaces of them often cover random textures that are dense and littery, which make against stereo matching. Reference to the form of human visual understanding of the natural environment, we propose computing the slant of slope using textures analysis of the monocular vision. Aiming at difficult of random textures analysis, radial competition method is presented for extracting texture elements which can reflect the size of texture elements and barycenter distributions of the same size texture are received by the statistic method. Based on this, we fit the tilt using Agglomerative Nesting Clustering and Linear method and compute the gradients using continental distance with varying weight. In the last, tilt computing experiment、slant and gradient calibration and algorithm applicability analysis are carried on. Experiment results show that the method can compute the tilt and slant of the surface effectively and the computing error is close to the estimate error of human vision. Furthermore, the method is little affected by gray scale.
4. Although the matching performance of color model algorithms exceed grey algorithm, the computing complexity of color model algorithms are higher than grey algorithm because of more similarity measures. For this problem, hardware accelerating system is designed using FPGA which has high ability of data parallel processing. In this paper, CMOS color image sensors HV7131B are used for image collection and Stratix FPGA EP1S30 is used for core processing module of the whole matching. A ping-pong 2-cache system is designed according to the transmission of HV7131B and the matching efficiency is improved in this way. In the phase of algorithm implementation, we adopt the system that matching in row unit and design 3-class gliding structure which can mitigate the time stress effectively. In this paper, we mostly design the accelerating system for the tache of the original matching cost computing using Series and Parallel turn System and Box filter technology. Also the real-time performance of improved L*a*b* and RGB algorithms are analyzed and compared according to the logical function and time simulation in Quartus. The simulation results show that the time complexity of improved L*a*b* is 1.1times higher than RGB algorithm.
引文
[1] 桑建学.越野环境下自主车仿真系统的研究.国防科学技术大学,2005
[2] 欧青立,何克忠.室外智能移动机器人的发展及其关键技术研究.机器人,2000,22(6):519-526
[3] 巩绪生,史美萍,贺汉根,李焱.越野环境建模与动态路径规划.计算机应用,2006,26(12):3039-3042
[4] 吴东晖.智能移动机器人的视觉导航技术.浙江大学,2001
[5] 于春和,刘济林.越野环境的三维地图重建.南京理工大学学报,2007,31(2):180-183
[6] 王 志 文 , 郭 戈 . 移 动 机 器 人 导 航 技 术 现 状 与 展 望 . 机 器 人 ,2003,25(5):470-474
[7] 蔡自兴,贺汉根,陈虹.未知环境中移动机器人导航控制研究的若干问题.控制与决策,2002,17(4):385-390
[8] 项志宇.针对越野自主导航的障碍物检测系统.东南大学学报,2005,35(S2):71-74
[9] 陈熙霖.视觉计算—人类感知能力的延伸.测控技术,2000,19(5):7-14
[10] 赵杰,于舒春,蔡鹤皋.金字塔双层动态规划立体匹配算法.控制与决策,2007,22(1): 69-72
[11] 顾 征 , 苏 显 渝 . 采 用 色 彩 相 似 性 约 束 的 立 体 匹 配 . 光 电 工 程 ,2007,34(1):95-99
[12] 徐奕,周军,周源华.立体视觉匹配技术.计算机工程与应用,2003,39(15):1-5
[13] 陈宇峰,谭文静,王海涛,王阳生.光度立体三维重建算法.计算机辅助设计与图形学学报,2005,17(11):2408-2414
[14] 李德仁,王新华,黄培之.基于光度立体的物体三维表面重建.测绘学报,1995,24(3):197-203
[15] 黄士科,陶琳,张天序.一种改进的基于光流的运动目标检测方法.华中科技大学学报,2005,33(5):39-41
[16] 杨文杰,胡明昊,杨静宇.一种基于光流的障碍物估计算法.计算机工程与应用,2006,42(5):80-81
[17] 胡庭波,吴涛,贺汉根.基于立体匹配技术的光流场计算方法.计算机工程与科学,2006,28(10):50-53
[18] Zheng Q, Chellappa R. Estimation of illuminant direction, albedo and shape from shading [J]. IEEE Trans on PAMI, 1991, 13(17):680-702
[19] 朱淼良,杨建刚,吴春明.自主式智能系统.浙江:浙江大学出版社,2000
[20] 李纬.移动机器人避障双目立体视觉算法研究.南京理工大学,2006
[21] 胡庭波.立体匹配技术及其在移动机器人中的应用.国防科学技术大学,2005
[22] 寿天德.视觉信息处理的脑机制.上海:上海科学教育出版社,1997
[23] 荆其诚,焦书兰,纪桂萍.人类的视觉.北京:科学出版社,1987
[24] 刘子辉.军用无人驾驶车辆非结构化道路识别方法研究.吉林大学,2007
[25] 孙承琦.基于视觉的机器人环境感知系统研究.中国民用航空学院,2004
[26] 杨少春,王克奇,戴天虹,白雪冰.基于 L*a*b*颜色空间对木材分类的研究.林业机械与木工设备,2007,35(10):28-30
[27] 于春和,刘济林.越野环境下基于四线激光雷达的障碍检测.南京理工大学学报,2006,30(5):618-625
[28] 宰小涛,赵宇明.基于 SIFT 特征描述子的立体匹配算法.微计算机信息,2007,23(8-3):285-287
[29] 林国余,张为公.基于控制点的分层双向动态规划立体匹配算法.信息与控制,2006,35(3):411-416
[30] 毕胜,梁德群.基于人类视觉特性的纹理分割方法.计算机应用,2006,26(5):1015-1017
[31] Arakawa K, Krotkov E. Fractal modeling of natural terrain: analysis and surface reconstruction with range data [J].Graphical Models and Image Processing, 1996, 58 (5):413-436
[32] 章毓晋.图像工程.北京:清华大学出版社,1999
[33] 吴继华,王诚.Altera FPGA/CPLD 设计.北京:人民邮电出版社,2005
[34] 林灶生,刘绍汉.Verilog FPGA 芯片设计.北京:北京航空航天大学出版社,2006
[35] Sugimoto S, Tateda H, Takahashi H. Obstacle detection using millimeter-wave radar and its visualization on image sequence[C] //Proceedings of International Conference on Pattern Recognition, IEEE, Washington ,USA 2004: 342-345
[36] 周文晖,杜歆,叶秀清,顾伟康.基于 FPGA 的双目立体视觉系统.中国图象图形学报,2005,10(9):1166-1170
[37] Zhang Z H, Weiss R, Hanson A R. Obstacle detection based on qualitative and quantitative 3D Reconstruction[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19(1):15-26
[38] 杜歆,厉晓华,顾伟康,丁蒋霖.区域法立体匹配的实时性问题研究.浙江大学学报,2003,30(6):628-631
[39] 张敏,刘培志,徐英新,王晋华.地面无人作战平台环境感知关键技术研究.车辆与动力技术,2007(2):44-47
[40] Blostein D, Ahuja N. Shape from texture: integrating texture-element extraction and surface estimation [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1989, 11(12):1233-1251
[41] 杜歆,陈华华.基于 TMS320C64x 的立体匹配实时性问题研究.传感技术学报,2005, 18(2):381-384
[42] 刘华军,陆建峰,杨静宇.基于相对特征的越野地形可通行性分析.数据采集与处理,2006,21(1):58-63
[43] 赵一兵,王荣本,李琳辉,金立生,郭烈.基于激光雷达的无人驾驶车前方障碍物检测.交通与计算机,2007,25(2):9-13
[44] 胡晓鹏.双目立体图像的快速匹配值计算方法.微计算机信息, 2007,24, (5):293-294
[45] 周秀芝,文贡坚,王润生.自适应窗口快速立体匹配.计算机学报,2006,29(3): 473-479
[46] Pentland A. Fractal-based description of natural scenes [J].IEEE Trans on Pattern Analysis and Machine Intelligence, 1984, 6(6):661-674
[47] 黄凯奇,王桥,吴镇扬.基于视觉特性和颜色空间的多尺度彩色图像增强算法.电子学报,2004,32(4):673-676
[48] 何友兵,李大海,王琼华.基于彩色图像的立体匹配算法.第二届立体图像技术及其应用(国际)研讨会论文集,2007
[49] 刘光.C++Builder 程序设计导学.北京:清华大学出版社,2002
[50] 刘凌,胡永生.数字信号处理的 FPGA 实现.北京:清华大学出版社,2003
[51] 蔡自兴.人工智能及其应用.第三版,北京:清华大学出版社,2004
[52] 陆宗骐.C/C++图像处理编程.北京:清华大学出版社,2005
[53] Ribeiro E, Hancock E R. Texture plane orientation from spectral accumulation [C] // Proceedings of International Conference on Pattern Recognition. Barcelona, Spain: IEEE, 2000:1802-1806
[54] Nils J.Nilsson.人工智能.北京:机械工业出版社,2003
[55] 廉玉生,王秀泽.5 种不同颜色空间的均匀性研究.测绘科学技术学报,2007,24 (2):104-106
[56] 陶霖密,徐光祐.机器视觉中的颜色问题及应用.科学通报,2001,46(3):177-189
[57] 郑元林,杨淑蕙,周世生,曹从军.CIE1976LAB 色差公式的均匀性研究.包装工程,2005,26(2):48-49
[58] 蒋亚军.三种常用颜色模型的比较研究.湖南科技学院学报,2007,28(4):37-38
[59] 刘浩学.CIE 均匀颜色空间与色差公式的应用.北京印刷学院学报,2003,11(3):3-8
[60] 候建,齐乃明.月球车立体视觉系统的一种实现方案.中国宇航学会深空探测技术专业委员会第一届学术会议,2005
[61] 朱志刚,石定机.数字图像处理.北京:电子工业出版社,2000
[62] Ribeiro E, Hancock E R. Shape from periodic texture using the eigenvectors of local affine distortion [J].IEEE Trans on Pattern Analysis and Machine Intelligence, 2001,23 (12):1459-1465
[63] Lobay A, Forsyth D A. Recovering shape and irradiance maps from rich dense texton fields[C] //Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, D.C., USA: IEEE, 2004:400-406
[64] Blake A, Marinos. Shape from texture: estimation, isotropy and moments [J]. Artificial Intelligence, 1990, 45(3):323-380
[65] Clerc M, Mallat S. The texture gradient equation for recovering shape from texture[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(4):536-539
[66] Forsyth D A. Shape from texture and integrability [C]// Proceedings of IEEE International Conference on Computer Vision. Vancouver, B.C., Canada: IEEE, 2001: 447-452
[67] White R, Forsyth D A. Combining cues: shape from shading and texture[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, NY: IEEE, 2006:1809-1816
[68] Kovesi P. Shapelets correlated with surface normals produce surfaces[C]//Proceedings of the IEEE International Conference on ComputerVision. Beijing, China: IEEE, 2005: 994-1001
[69] Krumm J, Shafer S A. Texture segmentation and shape in the same image[C]//Proceedings of IEEE International Conference on Computer Vision. Cambridge, Massachusetts: IEEE, 1995:121-127
[70] 李德广,李科杰,高丽丽,基于多尺度多方向相位匹配的立体视觉方法.仪器仪表学报,2004,25(S4):600-602
[71] Linhui Li, Rongben Wang, Mingheng Zhang. Study on stereo vision-based cross-country obstacle detection technology for intelligent vehicle [C] //Proceedings of the IEEE International Conference on Natural Computation. Washington, USA, IEEE 2007:719-723
[72] Manduchi R, Castano A, Talukder A, Matthies L. Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation [J]. Autonomous Robots, 2005, 18(1):81-102
[73] Cochran S D, Medioni G.3-D surface description from binocular stereo [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(10):981-994
[74] Tomasi C, Manduchi R. Stereo matching as a nearest-neighbor problem[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):333-340
[75] Lin M H, Tomasi C. Surfaces with occlusions from layered stereo [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8):1073-1078
[76] Gong M, Yang Y H. Fast Unambiguous Stereo Matching Using Reliability-Based Dynamic Programming [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6):998-1003
[77] 于枫,张丽英,廖宗建.ALTERA 可编程逻辑器件应用技术.北京:科学出版社,2004
[78] 徐奕,周军,周源华.基于小波及动态规划的相位匹配.上海交通大学学报,2003,37(3):388-392
[79] 吴涛,刘欣.基于单双目视觉信息融合的障碍检测方法.中国宇航学会深空探测技术专业委员会第二届学术会议论文集,2005
[80] 郭龙源,夏永泉,杨静宇.一种改进的彩色图像匹配算法.计算机工程与应用,2007,43(27):98-99
[81] 周东翔,蔡宣平,孙茂印.基于灰度段的立体匹配算法.软件学报,2001,12 (7):1101-1106
[82] 高 富 强 , 张 帆 . 一 种 快 速 彩 色 图 像 匹 配 算 法 . 计 算 机 应 用 ,2005,25(11):2604-2605
[2] 欧青立,何克忠.室外智能移动机器人的发展及其关键技术研究.机器人,2000,22(6):519-526
[3] 巩绪生,史美萍,贺汉根,李焱.越野环境建模与动态路径规划.计算机应用,2006,26(12):3039-3042
[4] 吴东晖.智能移动机器人的视觉导航技术.浙江大学,2001
[5] 于春和,刘济林.越野环境的三维地图重建.南京理工大学学报,2007,31(2):180-183
[6] 王 志 文 , 郭 戈 . 移 动 机 器 人 导 航 技 术 现 状 与 展 望 . 机 器 人 ,2003,25(5):470-474
[7] 蔡自兴,贺汉根,陈虹.未知环境中移动机器人导航控制研究的若干问题.控制与决策,2002,17(4):385-390
[8] 项志宇.针对越野自主导航的障碍物检测系统.东南大学学报,2005,35(S2):71-74
[9] 陈熙霖.视觉计算—人类感知能力的延伸.测控技术,2000,19(5):7-14
[10] 赵杰,于舒春,蔡鹤皋.金字塔双层动态规划立体匹配算法.控制与决策,2007,22(1): 69-72
[11] 顾 征 , 苏 显 渝 . 采 用 色 彩 相 似 性 约 束 的 立 体 匹 配 . 光 电 工 程 ,2007,34(1):95-99
[12] 徐奕,周军,周源华.立体视觉匹配技术.计算机工程与应用,2003,39(15):1-5
[13] 陈宇峰,谭文静,王海涛,王阳生.光度立体三维重建算法.计算机辅助设计与图形学学报,2005,17(11):2408-2414
[14] 李德仁,王新华,黄培之.基于光度立体的物体三维表面重建.测绘学报,1995,24(3):197-203
[15] 黄士科,陶琳,张天序.一种改进的基于光流的运动目标检测方法.华中科技大学学报,2005,33(5):39-41
[16] 杨文杰,胡明昊,杨静宇.一种基于光流的障碍物估计算法.计算机工程与应用,2006,42(5):80-81
[17] 胡庭波,吴涛,贺汉根.基于立体匹配技术的光流场计算方法.计算机工程与科学,2006,28(10):50-53
[18] Zheng Q, Chellappa R. Estimation of illuminant direction, albedo and shape from shading [J]. IEEE Trans on PAMI, 1991, 13(17):680-702
[19] 朱淼良,杨建刚,吴春明.自主式智能系统.浙江:浙江大学出版社,2000
[20] 李纬.移动机器人避障双目立体视觉算法研究.南京理工大学,2006
[21] 胡庭波.立体匹配技术及其在移动机器人中的应用.国防科学技术大学,2005
[22] 寿天德.视觉信息处理的脑机制.上海:上海科学教育出版社,1997
[23] 荆其诚,焦书兰,纪桂萍.人类的视觉.北京:科学出版社,1987
[24] 刘子辉.军用无人驾驶车辆非结构化道路识别方法研究.吉林大学,2007
[25] 孙承琦.基于视觉的机器人环境感知系统研究.中国民用航空学院,2004
[26] 杨少春,王克奇,戴天虹,白雪冰.基于 L*a*b*颜色空间对木材分类的研究.林业机械与木工设备,2007,35(10):28-30
[27] 于春和,刘济林.越野环境下基于四线激光雷达的障碍检测.南京理工大学学报,2006,30(5):618-625
[28] 宰小涛,赵宇明.基于 SIFT 特征描述子的立体匹配算法.微计算机信息,2007,23(8-3):285-287
[29] 林国余,张为公.基于控制点的分层双向动态规划立体匹配算法.信息与控制,2006,35(3):411-416
[30] 毕胜,梁德群.基于人类视觉特性的纹理分割方法.计算机应用,2006,26(5):1015-1017
[31] Arakawa K, Krotkov E. Fractal modeling of natural terrain: analysis and surface reconstruction with range data [J].Graphical Models and Image Processing, 1996, 58 (5):413-436
[32] 章毓晋.图像工程.北京:清华大学出版社,1999
[33] 吴继华,王诚.Altera FPGA/CPLD 设计.北京:人民邮电出版社,2005
[34] 林灶生,刘绍汉.Verilog FPGA 芯片设计.北京:北京航空航天大学出版社,2006
[35] Sugimoto S, Tateda H, Takahashi H. Obstacle detection using millimeter-wave radar and its visualization on image sequence[C] //Proceedings of International Conference on Pattern Recognition, IEEE, Washington ,USA 2004: 342-345
[36] 周文晖,杜歆,叶秀清,顾伟康.基于 FPGA 的双目立体视觉系统.中国图象图形学报,2005,10(9):1166-1170
[37] Zhang Z H, Weiss R, Hanson A R. Obstacle detection based on qualitative and quantitative 3D Reconstruction[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19(1):15-26
[38] 杜歆,厉晓华,顾伟康,丁蒋霖.区域法立体匹配的实时性问题研究.浙江大学学报,2003,30(6):628-631
[39] 张敏,刘培志,徐英新,王晋华.地面无人作战平台环境感知关键技术研究.车辆与动力技术,2007(2):44-47
[40] Blostein D, Ahuja N. Shape from texture: integrating texture-element extraction and surface estimation [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1989, 11(12):1233-1251
[41] 杜歆,陈华华.基于 TMS320C64x 的立体匹配实时性问题研究.传感技术学报,2005, 18(2):381-384
[42] 刘华军,陆建峰,杨静宇.基于相对特征的越野地形可通行性分析.数据采集与处理,2006,21(1):58-63
[43] 赵一兵,王荣本,李琳辉,金立生,郭烈.基于激光雷达的无人驾驶车前方障碍物检测.交通与计算机,2007,25(2):9-13
[44] 胡晓鹏.双目立体图像的快速匹配值计算方法.微计算机信息, 2007,24, (5):293-294
[45] 周秀芝,文贡坚,王润生.自适应窗口快速立体匹配.计算机学报,2006,29(3): 473-479
[46] Pentland A. Fractal-based description of natural scenes [J].IEEE Trans on Pattern Analysis and Machine Intelligence, 1984, 6(6):661-674
[47] 黄凯奇,王桥,吴镇扬.基于视觉特性和颜色空间的多尺度彩色图像增强算法.电子学报,2004,32(4):673-676
[48] 何友兵,李大海,王琼华.基于彩色图像的立体匹配算法.第二届立体图像技术及其应用(国际)研讨会论文集,2007
[49] 刘光.C++Builder 程序设计导学.北京:清华大学出版社,2002
[50] 刘凌,胡永生.数字信号处理的 FPGA 实现.北京:清华大学出版社,2003
[51] 蔡自兴.人工智能及其应用.第三版,北京:清华大学出版社,2004
[52] 陆宗骐.C/C++图像处理编程.北京:清华大学出版社,2005
[53] Ribeiro E, Hancock E R. Texture plane orientation from spectral accumulation [C] // Proceedings of International Conference on Pattern Recognition. Barcelona, Spain: IEEE, 2000:1802-1806
[54] Nils J.Nilsson.人工智能.北京:机械工业出版社,2003
[55] 廉玉生,王秀泽.5 种不同颜色空间的均匀性研究.测绘科学技术学报,2007,24 (2):104-106
[56] 陶霖密,徐光祐.机器视觉中的颜色问题及应用.科学通报,2001,46(3):177-189
[57] 郑元林,杨淑蕙,周世生,曹从军.CIE1976LAB 色差公式的均匀性研究.包装工程,2005,26(2):48-49
[58] 蒋亚军.三种常用颜色模型的比较研究.湖南科技学院学报,2007,28(4):37-38
[59] 刘浩学.CIE 均匀颜色空间与色差公式的应用.北京印刷学院学报,2003,11(3):3-8
[60] 候建,齐乃明.月球车立体视觉系统的一种实现方案.中国宇航学会深空探测技术专业委员会第一届学术会议,2005
[61] 朱志刚,石定机.数字图像处理.北京:电子工业出版社,2000
[62] Ribeiro E, Hancock E R. Shape from periodic texture using the eigenvectors of local affine distortion [J].IEEE Trans on Pattern Analysis and Machine Intelligence, 2001,23 (12):1459-1465
[63] Lobay A, Forsyth D A. Recovering shape and irradiance maps from rich dense texton fields[C] //Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, D.C., USA: IEEE, 2004:400-406
[64] Blake A, Marinos. Shape from texture: estimation, isotropy and moments [J]. Artificial Intelligence, 1990, 45(3):323-380
[65] Clerc M, Mallat S. The texture gradient equation for recovering shape from texture[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(4):536-539
[66] Forsyth D A. Shape from texture and integrability [C]// Proceedings of IEEE International Conference on Computer Vision. Vancouver, B.C., Canada: IEEE, 2001: 447-452
[67] White R, Forsyth D A. Combining cues: shape from shading and texture[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, NY: IEEE, 2006:1809-1816
[68] Kovesi P. Shapelets correlated with surface normals produce surfaces[C]//Proceedings of the IEEE International Conference on ComputerVision. Beijing, China: IEEE, 2005: 994-1001
[69] Krumm J, Shafer S A. Texture segmentation and shape in the same image[C]//Proceedings of IEEE International Conference on Computer Vision. Cambridge, Massachusetts: IEEE, 1995:121-127
[70] 李德广,李科杰,高丽丽,基于多尺度多方向相位匹配的立体视觉方法.仪器仪表学报,2004,25(S4):600-602
[71] Linhui Li, Rongben Wang, Mingheng Zhang. Study on stereo vision-based cross-country obstacle detection technology for intelligent vehicle [C] //Proceedings of the IEEE International Conference on Natural Computation. Washington, USA, IEEE 2007:719-723
[72] Manduchi R, Castano A, Talukder A, Matthies L. Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation [J]. Autonomous Robots, 2005, 18(1):81-102
[73] Cochran S D, Medioni G.3-D surface description from binocular stereo [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(10):981-994
[74] Tomasi C, Manduchi R. Stereo matching as a nearest-neighbor problem[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):333-340
[75] Lin M H, Tomasi C. Surfaces with occlusions from layered stereo [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8):1073-1078
[76] Gong M, Yang Y H. Fast Unambiguous Stereo Matching Using Reliability-Based Dynamic Programming [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6):998-1003
[77] 于枫,张丽英,廖宗建.ALTERA 可编程逻辑器件应用技术.北京:科学出版社,2004
[78] 徐奕,周军,周源华.基于小波及动态规划的相位匹配.上海交通大学学报,2003,37(3):388-392
[79] 吴涛,刘欣.基于单双目视觉信息融合的障碍检测方法.中国宇航学会深空探测技术专业委员会第二届学术会议论文集,2005
[80] 郭龙源,夏永泉,杨静宇.一种改进的彩色图像匹配算法.计算机工程与应用,2007,43(27):98-99
[81] 周东翔,蔡宣平,孙茂印.基于灰度段的立体匹配算法.软件学报,2001,12 (7):1101-1106
[82] 高 富 强 , 张 帆 . 一 种 快 速 彩 色 图 像 匹 配 算 法 . 计 算 机 应 用 ,2005,25(11):2604-2605