移动机器人全景视觉归航技术研究
|
摘要
导航是实现机器人智能化和完全自主移动的关键技术。视觉导航具有探测范围广获取信息量大等优点,是移动机器人重要的研究方向。然而,传统的视觉导航方法需要建立环境的精确模型,解决地图创建与同时定位问题(SLAM),算法的空间复杂度较高,扩展应用困难。受昆虫类生物导航原理的启发,视觉归航方法将传统视觉导航中的定位与地图创建工作转化为对运行方向和停止位置的判断,不需要建立环境的精确模型,占用存储空间小,导航过程中没有累积误差,导航精度不受距离的影响,是视觉导航领域一个新的研究方向。本文采用全景视觉传感器对基于自然路标的机器人归航技术进行了深入研究。
论文首先研究了全景图像中的自然路标提取问题。在非结构化环境中不存在人工路标,机器人要实现归航只能依靠环境中的自然路标。对比多种自然路标提取方法,图像局部特征具有多种不变性,特征点定位准确,非常适合作为自然路标点。SIFT和SURF是两种高效的斑点提取算法,以其优异的性能受到越来越多学者的关注。然而,这两种算法在全景图像中的特征提取性能,还没有被评估过。为了获得环境中性能稳定的自然路标点,本文采用重复率、匹配率、错误匹配率三个标准评估了SIFT和SURF在全景图像中的特征适应性。同时为了评估路标分布的均匀度,提出了特征分布均匀性的量化评估标准,并对SIFT和SURF在多种环境下的特征分布均匀性进行了评估。
其次解决自然路标点之间的对应性问题。由于直接通过检索方法得到的最近邻匹配并不能保证完全正确,而错误的自然路标匹配会导致归航决策偏离正确方向,甚至会导致归航失败,因此必须对匹配结果进行提纯。原始匹配结果中存在多个路标对应一个路标的问题(多对一),文中提出了一种改进的匹配方法,消除路标匹配中的多对一问题,增强匹配的稳定性。针对全景图像中的错误匹配问题,提出了基于角度估算和基于最长公共子序列的误匹配消除方法,提纯自然路标。
在完成了自然路标提取、匹配、提纯的基础上,本文给出了平均位移向量归航方法、平均路标向量归航方法的实现过程,首次完整表述了基于路标夹角差的归航方法。构建了完整的实验系统,采用推算式定位方法记录机器人在实验过程中的轨迹,对履带打滑进行补偿,利用全景视觉校正机器人的方位角,提高推算式定位方法的精度。在本文的实验环境中,对比了ADV、ALV和夹角差三种基于路标的归航方法,分析了每种方法的优缺点,并据此提出局部归航中的优化方法。针对ALV、ADV方法需要已知Home位置方位角的限制,采用基于角度估算的方法来减弱限制。对归航中的自然路标点进行优化,控制特征提取的数量、质量和均匀度。利用ADV和夹角差归航方法的优点,采用模糊控制策略,提出一种融合式归航方法。
最后针对局部归航作用距离过短问题进行了初步研究。采用增加中间节点的方式,引导机器人沿着多个中间节点到达最终的Home位置。以拓扑地图的形式,组织中间节点,并使机器人在离开H0me位置时自动创建拓扑地图。
Navigation is the key technology of achieving robot intelligence and autonomous mobile. Visual navigation can detect a wider range and get much more information, that is important to research mobile robot in the future. However, the precise model of environment must be established in traditional navigation methods. For example, SLAM(simultaneous localization and mapping) has a higher space complexity and more difficult extended application. Visual homing is a method of behavior-based navigation, which has been inspired by the principle of biological navigation. These methods change the simultaneous localization and mapping to determine the running direction and stop position. So it is more similar to intelligent life navigation. Visual homing does not need an accurate environmental model, and it occupies less storage space.. There is no accumulation error during navigation, so the accuracy is not affected from the distance. This paper deeply studied robot visual homing based on natural landmark used panoramic vision sensor.
First, we studied on extracting natural landmark from the panoramic image. Because there are not artificial landmarks in the unstructured environment, so the robot can only rely on the natural landmarks of environment to achieve homing. Comparing a variety of methods of extracting natural landmark, local feature has many invariance and it is suitable as natural landmark points. SIFT and SURF are two efficient and robust spot extracting methods, so more and more scholars began to focus on them. But their performances in panoramic image had not been evaluated. In order to obtain stable natural landmark points, we evaluated the performance of SIFT and SURF using repeatability, match rate and mismatch rate. At the same time, a method of evaluating distribution uniformity of feature points has been proposed. And we assessed the distribution uniformity of SIFT and SURF feature points in different environment.
Second, we calculated relevance of natural landmarks. Because mismatch will interfere with deviating from right direction during homing and even failed homing. So the matched natural landmarks must be purified. If using the previous matching results, there will be many landmarks matching to one landmark. And it is incorrect or unstable. In this paper, an improved matching method to solve this problem has been proposed. To solve the mismatching problem in panoramic image, two methods of eliminating mismatches have been also presented in this paper, which were based on angle estimation and the longest common subsequence.
After completion of extraction, matching, purification of natural landmarks, the visual homing method based on natural landmarks were given, which included average displacement vector method, average landmark vector method. And the homing method based on angle difference was firstly completely described. Homing experiment system was constructed and moving track of robot was recorded by dead reckoning method. To improve the positioning accuracy, the robot tracked skid was compensated and azimuth error was corrected using angle estimation based on panoramic vision. We compared of ADV, ALV and the included angle difference based on landmarks in our test environment. Because ADV、ALV must have known(should know) the azimuth of home position, we reduced the constraints by angle estimation.
Finally, we simply studied the long range visual homing. We increased the number of intermediate home targets, and used multiple intermediate nodes to guide the robot to reach the last home position. Intermediate nodes are organized in the form of a topological map, and the robot can automatically creates a topological map after leaving home position.
论文首先研究了全景图像中的自然路标提取问题。在非结构化环境中不存在人工路标,机器人要实现归航只能依靠环境中的自然路标。对比多种自然路标提取方法,图像局部特征具有多种不变性,特征点定位准确,非常适合作为自然路标点。SIFT和SURF是两种高效的斑点提取算法,以其优异的性能受到越来越多学者的关注。然而,这两种算法在全景图像中的特征提取性能,还没有被评估过。为了获得环境中性能稳定的自然路标点,本文采用重复率、匹配率、错误匹配率三个标准评估了SIFT和SURF在全景图像中的特征适应性。同时为了评估路标分布的均匀度,提出了特征分布均匀性的量化评估标准,并对SIFT和SURF在多种环境下的特征分布均匀性进行了评估。
其次解决自然路标点之间的对应性问题。由于直接通过检索方法得到的最近邻匹配并不能保证完全正确,而错误的自然路标匹配会导致归航决策偏离正确方向,甚至会导致归航失败,因此必须对匹配结果进行提纯。原始匹配结果中存在多个路标对应一个路标的问题(多对一),文中提出了一种改进的匹配方法,消除路标匹配中的多对一问题,增强匹配的稳定性。针对全景图像中的错误匹配问题,提出了基于角度估算和基于最长公共子序列的误匹配消除方法,提纯自然路标。
在完成了自然路标提取、匹配、提纯的基础上,本文给出了平均位移向量归航方法、平均路标向量归航方法的实现过程,首次完整表述了基于路标夹角差的归航方法。构建了完整的实验系统,采用推算式定位方法记录机器人在实验过程中的轨迹,对履带打滑进行补偿,利用全景视觉校正机器人的方位角,提高推算式定位方法的精度。在本文的实验环境中,对比了ADV、ALV和夹角差三种基于路标的归航方法,分析了每种方法的优缺点,并据此提出局部归航中的优化方法。针对ALV、ADV方法需要已知Home位置方位角的限制,采用基于角度估算的方法来减弱限制。对归航中的自然路标点进行优化,控制特征提取的数量、质量和均匀度。利用ADV和夹角差归航方法的优点,采用模糊控制策略,提出一种融合式归航方法。
最后针对局部归航作用距离过短问题进行了初步研究。采用增加中间节点的方式,引导机器人沿着多个中间节点到达最终的Home位置。以拓扑地图的形式,组织中间节点,并使机器人在离开H0me位置时自动创建拓扑地图。
Navigation is the key technology of achieving robot intelligence and autonomous mobile. Visual navigation can detect a wider range and get much more information, that is important to research mobile robot in the future. However, the precise model of environment must be established in traditional navigation methods. For example, SLAM(simultaneous localization and mapping) has a higher space complexity and more difficult extended application. Visual homing is a method of behavior-based navigation, which has been inspired by the principle of biological navigation. These methods change the simultaneous localization and mapping to determine the running direction and stop position. So it is more similar to intelligent life navigation. Visual homing does not need an accurate environmental model, and it occupies less storage space.. There is no accumulation error during navigation, so the accuracy is not affected from the distance. This paper deeply studied robot visual homing based on natural landmark used panoramic vision sensor.
First, we studied on extracting natural landmark from the panoramic image. Because there are not artificial landmarks in the unstructured environment, so the robot can only rely on the natural landmarks of environment to achieve homing. Comparing a variety of methods of extracting natural landmark, local feature has many invariance and it is suitable as natural landmark points. SIFT and SURF are two efficient and robust spot extracting methods, so more and more scholars began to focus on them. But their performances in panoramic image had not been evaluated. In order to obtain stable natural landmark points, we evaluated the performance of SIFT and SURF using repeatability, match rate and mismatch rate. At the same time, a method of evaluating distribution uniformity of feature points has been proposed. And we assessed the distribution uniformity of SIFT and SURF feature points in different environment.
Second, we calculated relevance of natural landmarks. Because mismatch will interfere with deviating from right direction during homing and even failed homing. So the matched natural landmarks must be purified. If using the previous matching results, there will be many landmarks matching to one landmark. And it is incorrect or unstable. In this paper, an improved matching method to solve this problem has been proposed. To solve the mismatching problem in panoramic image, two methods of eliminating mismatches have been also presented in this paper, which were based on angle estimation and the longest common subsequence.
After completion of extraction, matching, purification of natural landmarks, the visual homing method based on natural landmarks were given, which included average displacement vector method, average landmark vector method. And the homing method based on angle difference was firstly completely described. Homing experiment system was constructed and moving track of robot was recorded by dead reckoning method. To improve the positioning accuracy, the robot tracked skid was compensated and azimuth error was corrected using angle estimation based on panoramic vision. We compared of ADV, ALV and the included angle difference based on landmarks in our test environment. Because ADV、ALV must have known(should know) the azimuth of home position, we reduced the constraints by angle estimation.
Finally, we simply studied the long range visual homing. We increased the number of intermediate home targets, and used multiple intermediate nodes to guide the robot to reach the last home position. Intermediate nodes are organized in the form of a topological map, and the robot can automatically creates a topological map after leaving home position.
引文
[1]焦震,高海波,邓宗全,et al.基于地面力学的月球车爬坡轮—地相互作用模型[J].机器人.2010,32(1)：70-76页
[2]孟彦鹏,王永,谢圆,et al.基于Creator/Vega的月球车轮地交互仿真[J].机器人.2010,32(3)：369-374页
[3]陈勇,桂卫华,王随平.深海采矿机器人控制体系结构研究[J].控制工程.2009,16(4)：488-490页
[4]Salichs M A, Moreno L. Navigation of mobile robots:Open questions[J]. Robotica. 2000,18(3):227-234页
[5]王璐.未知环境中移动机器人视觉环境建模与定位研究[D].中南大学博士学位论文,2007
[6]Davison A J, Murray D W. Simultaneous localization and map-building using active vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(7): 865-880P
[7]Davison A J, Reid I D, Molton N D, et al. MonoSLAM:Real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007,29(6): 1052-1067P
[8]Eade E, Drummond T. Edge landmarks in monocular SLAM[J]. Image and Vision Computing.2009,27(5):588-596P
[9]Pinies P, Tardos J D. Large-scale SLAM building conditionally independent local maps: Application to monocular vision[J]. IEEE Transactions on Robotics.2008,24(5): 1094-1106P
[10]Cheein F A, Scaglia G, Di Sciasio F, et al. Feature selection criteria for real time EKF-SLAM algorithm[J]. International Journal of Advanced Robotic Systems.2010, 7(2):115-124P
[11]赵立坤,武二永,郭羰平,et al.基于概率选取随机特征点的单目视觉SLAM方法[J].机器人.2010,32(05)：642-646页
[12]许俊勇,王景川,陈卫东.基于全景视觉的移动机器人同步定位与地图创建研究[J].机器人.2008,30(4)：289-297页.
[13]高明.基于全景视觉的单目SLAM系统[D].合肥工业大学硕士学位论文,2009
[14]Cheein F A, Scaglia G, Di Sciasio F, et al. Feature selection criteria for real time EKF-SLAM algorithm[J]. International Journal of Advanced Robotic Systems.2010, 7(2):115-124P
[15]Gil A, Reinoso O, Ballesta M, et al. Multi-robot visual SLAM using a Rao-Blackwellized particle filter[J]. Robotics and Autonomous Systems.2010,58(1): 68-80P
[16]陈凤东,洪炳镕.一种基于图像的移动机器人泊位方法[J].机器人.2010,32(2)：166-170页
[17]Hong J, Tan X, Pinette B, et al. Image-based homing[J]. IEEE Control Systems Magazine.1992,12(1):38-45P
[18]陆军,孙凌丽,穆海军,et al.基于全景视觉的机器人相互定位的研究[J].哈尔滨工程大学学报.2010,31(4)：457-464页
[19]Gro R, Bonani M, Mondada F, et al. Autonomous self-assembly in swarm-bots[J]. IEEE Transactions on Robotics.2006,22(6):1115-1130P
[20]Franz M O, Scholkopf B, Mallot H A, et al. Where did I take that snapshot? Scene-based homing by image matching[J]. Biological Cybernetics.1998,79(3):191P
[21]张帆.全景视觉图像质量优化方法研究[D].哈尔滨工程大学博士学位论文,2010
[22]工海军.未知环境下移动机器人即时定位与地图创建[D].上海大学博士学位论文,2009
[23]石朝侠,洪炳镕,周彤,et al.大规模环境下的拓扑地图创建与导航[J].机器人2007,29(5)：433-438页
[24]Wetherbie Iii J O, Smith C E. Large-scale feature identification for indoor topological mapping[C]. Tucson, AZ, United states:2001
[25]庄严,徐晓东,王伟.移动机器人几何-拓扑混合地图的构建及自定位研究[J].控制与决策.2005,20(07)：815-822页
[26]司秉玉.基于可视人工路标的自主机器人导航若干问题研究[D].东北大学博士学位论文,2003
[27]Becker C, Salas J, Tokusei K, et al. Reliable navigation using landmarks[C]. Nagoya, Jpn: 1995
[28]Taylor C J, Kriegman D J. Vision-based motion planning and exploration algorithms for mobile robots[J]. IEEE Transactions on Robotics and Automation.1998,14(3): 417-426P
[29]Zitova B, Flusser J. Landmark recognition using invariant features[J]. Pattern Recognition Letters.1999,20(5):541-547P
[30]胡英,赵姝颖,徐心和.色标设计与辨识算法研究[J].中国图象图形学报.2002,7(12)：1291-1295页
[31]董再励,郝颖明,朱枫.一种基于视觉的移动机器人定位系统[J].中国图象图形学报.2000(08)：687-692页
[32]沙超,王汝传,孙力娟,et al.无线传感器网络中一种信标节点可迁移的协作定位方法[J].电子学报.2010,38(11)：2625-2629页
[33]孙光民,王晶,于光宇,et al.自然背景中交通标志的检测与识别[J].北京工业大学学报.2010,36(10)：1337-1343页
[34]李伦波,马广富.自然场景下交通标志检测与分类算法研究[J].哈尔滨工业大学学报.2009,41(11)：29-38页
[35]Desouza G N, Kak A C. Vision for mobile robot navigation:A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(2):237-267P
[36]Kosaka A, Kak A C. Fast vision-guided mobile robot navigation using model-based reasoning and prediction of uncertainties[J]. CVGIP: Image Understanding.1992,56(3): 271-329P
[37]严永杰.多机器人系统协调与控制研究[D].哈尔滨工程大学博士学位论文,2007
[38]Argyros A A, Bekris K E, Orphanoudakis S C, et al. Robot homing by exploiting panoramic vision[J]. Autonomous Robots.2005,19(1):7-25P
[39]Se S, Lowe D G, Little J J. Vision-based global localization and mapping for mobile robots[J]. IEEE Transactions on Robotics.2005,21(3):364-375P
[40]Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision.2000,37(2):151-172P
[41]Mikolajczyk K, Schmid C. Scale affine invariant interest point detectors [J]. International Journal of Computer Vision.2004,60(1):63-86P
[42]雷明.图像特征的检测、描述及匹配[D].重庆大学硕士学位论文,2008
[43]C Harris M S. A combined corner and edge detector[Z]. Mancheste:1988,147-151P
[44]Mikolajzyk K. Detection of local features invariant to affine transformations[D]. Institut National Polytechnique de Grenoble,2002
[45]王永明,王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社,2010：203
[46]Mikolajczyk K, Leibe B, Schiele B. Local features for object class recognition[C]. Beijing, China:2005
[47]Lowe D G. Object recognition from local scale-invariant features[C]. Kerkyra, Greece: 1999
[48]Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision.2004,60(2):91-110P
[49]Lindeberg T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision.1998,30(2):79-116P
[50]Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features (SURF)[J]. Computer Vision and Image Understanding.2008,110(3):346-359P
[51]徐秀云.基于特征点的景象匹配技术研究[D].南京理工大学硕士学位论文,2009
[52]Matas J, Chum O, Urban M, et al. Robust wide-baseline stereo from maximally stable extremal regions[C].2004
[53]Tuytelaars T, Van Gool L. Matching widely separated views based on affine invariant regions[J]. International Journal of Computer Vision.2004,59(1):61-85P
[54]Tuytelaars T, Van Gool L. Wide baseline stereo matching based on local, affinely invariant regions[J].2000
[55]Kadir T, Brady M. Saliency, scale and image description[J]. International Journal of Computer Vision.2001,45(2):83-105P
[56]Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[C]. Madison, WI, United states:2003
[57]Ke Y, Sukthankar R. PCA-SIFT:A more distinctive representation for local image descriptors[C]. Washington, DC, United states:2004
[58]Belongie S, Malik J, Puzicha J. Shape context:A new descriptor for shape matching and object recognition[Z].2000,831-837P
[59]Koenderink J J, Doom A V. Representation of local geometry in the visual system[J]. Biological Cybernetics.1987,6(55):367-375P
[60]Van G L, Moons T, Ungureanu D. Affine/photometric invariants for planar intensity patterns[C]. Cambridge, United kingdom:1996
[61]万玮,冯学智,肖鹏峰,et al.基于傅里叶描述子的高分辨率遥感图像地物形状特征表达[J].遥感学报.2011,15(01)：73-87页
[62]封筠,穆志纯,毛晚堆.基于局部二值模式与滤波器融合的人耳识别[J].计算机工程与应用.2010,46(35)：192-195页
[63]Bowyer K, Kranenburg C, Dougherty S. Edge detector evaluation using empirical ROC curves [J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1999,1:354-359P
[64]Heath M, Sarkar S, Sanocki T, et al. Comparison of edge detectors. A methodology and initial study[J]. Computer Vision and Image Understanding.1998,69(1):38-54P
[65]Lopez A M, Lumbreras F, Serrat J, et al. Evaluation of methods for ridge and valley detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1999, 21(4):327-335P
[66]Brand P, Mohr R. Accuracy in image measure[C]. Boston, MA, USA:1994
[67]Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision.2000,37(2):151-172P
[68]李雷达,郭宝龙,表金峰.基于奇偶量化的空域抗几何攻击图像水印算法[J].电子与信息学报.2009,31(01)：134-138页
[69]徐紫涵,王向阳.可有效抵抗一般性几何攻击的数字水印检测方法[J].自动化学报.2009,35(01)：23-27页
[70]朱海峰,赵春晖.图像特征点分布均匀性的评价方法[J].大庆师范学院学报.2010,30(03)：9-12页
[71]Morris R G M. Spatial Localization Does Not Require the Presence of Local Cues[J]. Learning and Motivation.1981,2(12):239-260P
[72]Cartwright B A, Collett T S. Landmark maps for honeybees [J]. Biological Cybernetics. 1987,57(1-2):85-93P
[73]Cartwright B A, Collett T S C. Landmark learning in bees[J]. Journal of Comparative Physiology.1983,151:521-543P
[74]Wehner R. The desert ant's navigational toolkit: Procedural rather than positional knowledge[C].3975 University Drive, Suite 390, Fairfax, VA 22030, United States: 2008
[75]Knaden M, Wehner R. Path integration in desert ants controls aggressiveness[J]. Science. 2004,305(5680):60P
[76]Muller M, Wehner R. Path integration in desert ants, Cataglyphis fortis[J]. Proceedings of the National Academy of Sciences.1988,85(14):5287-5290P
[77]Judd S P D, Collett T S. Multiple stored views and landmark guidance in ants[J]. Nature. 1998,392(6677):710-714P
[78]Collett T S. Insect navigation en route to the goal:Multiple strategies for the use of landmarks[J]. Journal of Experimental Biology.1996,199:227-235P
[79]Horridge A. Pattern and 3d vision of insects [J]. In Visual Navigation.1997:26-59P
[80]Wehner R, Michel B, Antonsen P. Visual navigation in insects:Coupling of egocentric and geocentric information[J]. Journal of Experimental Biology.1996,199:129-140
[81]Rofer T, Ofer T R. Controlling a Wheelchair with Image-based Homing[C].1997
[82]Lambrinos D, Moller R, Labhart T, et al. Mobile robot employing insect strategies for navigation[J]. Robotics and Autonomous Systems.2000,30(1):39-64P
[83]Moller R. Insect visual homing strategies in a robot with analog processing[J]. Biological Cybernetics.2000,83(3):231-243P
[84]Gaussier P, Joulain C, Banquet J P, et al. The visual homing problem:An example of robotics/biology cross fertilization[J]. Robotics and Autonomous Systems.2000,30(1-2): 155-180P
[85]Basten K, Mallot H A. Simulated visual homing in desert ant natural environments: Efficiency of skyline cues[J]. Biological Cybernetics.2010,102(5):413-425P
[86]Franz M O, Scholkopf B, Mallot H A, et al. Where did I take that snapshot? Scene-based homing by image matching[J]. Biological Cybernetics.1998,79(3):191P
[87]Zeil J, Hofmann M I, Chahl J S. Catchment areas of panoramic snapshots in outdoor scenes[J]. Journal of the Optical Society of America A: Optics and Image Science, and Vision.2003,20(3):450-469P
[88]Binding D, Binding D, Labrosse F, et al. Visual local navigation using warped panoramic images[C].2006
[89]Sturzl W, Mallot H A. Efficient visual homing based on Fourier transformed panoramic images[J]. Robotics and Autonomous Systems.2006,54(4):300-313P
[90]郑重.非结构环境下的移动机器人路径规划算法研究[D].中国科学技术大学博士学位论文,2009
[91]Chunlin T, Hongqiao W, Deli P. SWF-SIFT Approach for Infrared Face Recognition[J]. Tsinghua Science and Technology.2010,15(03):357-362P
[92]Zhu Q, Li Ke. Image stitching using simplified SIFT[C]. Harbin, Heilongjiang, China: 2010
[93]关洪洋.图像融合与配准技术在掌纹图像中的应用[D].吉林大学硕士学位论文,2010
[94]Rao-Blackwellized滤波器实现机器人同时定位和地图创建[J].哈尔滨工业大学学报.2008,40(03)：401-406页
[95]Mikolajczyk K, Schmid C. Scale affine invariant interest point detectors[J]. International Journal of Computer Vision.2004,60(1):63-86P
[96]Wang Y, Lin M, Ju R, et al. Image feature initialization for SLAM and moving object detection[J]. ICIC Express Letters.2009,3(3):477-482P
[97]Li S, Chen T, Yu C, et al. SURF-based video mosaic and its key technologies[J]. Journal of Computational Information Systems.2010,6(10):3267-3276P
[98]An M, Jiang Z, Zhao D. High speed robust image registration and localization using optimized algorithm and its performances evaluation[J]. Journal of Systems Engineering and Electronics.2010,21(3):520-526P
[99]雷兰一菲,郎海涛.几种典型局部图像特征的比较[J].计算机应用.2010,30(S2)：50-53页
[100]Gil A, Mozos O M, Ballesta M, et al. A comparative evaluation of interest point detectors and local descriptors for visual SLAM[J]. Machine Vision and Applications. 2010,21(6):905-920P
[101]Rochdi B, Kamel B. Comparative study of interest point detectors and descriptors for automatic remote-sensing image registration[J]. International Review on Computers and Software.2010,5(3):264-275P
[102]熊智,陈方,王丹,et al.SAR/INS组合导航中基于SURF的鲁棒景象匹配算法[J].南京航空航天大学学报.2011,43(01)：49-54页
[103]谭正华,王李管,陈建宏,et al.基于KD树的露天矿采场示坡线自动生成方法[J].计算机应用.2010,30(07)：1840-1938页
[104]潘章明.一种基于KD树子样的自动聚类方法[J].计算机工程与科学.2011,33(01)：166-170页
[105]贾广利,魏娟,马宏伟.一种六履带侦查机器人的运动分析及结构设计[J].机床与液压.2008,36(11)：8-10页
[106]滕赞,姚辰,王挺,et al.变形履带轮椅机器人的张紧力最优估计和越障能力分析[J].机器人.2010,32(5)：622-629页
[107]李允旺,葛世荣,朱华.摇杆式履带悬架的构型推衍及其在煤矿救灾机器人上的应用[J].机器人.2010(1)：25-33页
[108]Dean A J, Brennan S N. A low-order dynamic model of a tracked robot inclusive of non-linear slip[J].International Journal of Heavy Vehicle Systems.2008,15(2-4): 327-355P
[109]孙自广,李春贵,王秦.基于改进遗传算法的机器人路径规划[J].自动化与仪表.2009,24(6)：5-7页
[110]陶敏,陈新,孙振平.移动机器人定位技术[J].火力与指挥控制.2010,35(7)：169-172页
[111]白冰洋,沈阳.推算定位算法在拦截策略中的研究与应用[J].计算机仿真.2009,26(3)：169-171页
[112]Bevly D M, Parkinson B. Cascaded Kalman filters for accurate estimation of multiple biases, dead-reckoning navigation, and full state feedback control of ground vehicles[J]. IEEE Transactions on Control Systems Technology.2007,15(2):199-208P
[113]Azenha A, Carvalho A. Dynamic analysis of AGV control under dead-reckoning algorithm[J]. Robotica.2008,26(5):635-641P
[114]温素芳.基于模糊控制的移动机器人动态避碰的研究[D].哈尔滨工程大学硕士学位论文,2005
[115]蔡建羡,阮晓钢,郜园园.随机模糊控制策略及其在机器人控制中的应用[J].电机与控制学报.2009,13(5)：754-761页
[116]徐国政,宋爱国,李会军.基于模糊逻辑的上肢康复机器人阻抗控制实验研究[J].机器人.2010,32(6)：792-798页
[117]康亮,赵春霞,郭剑辉.基于模糊滚动RRT算法的移动机器人路径规划[J].南京理工大学学报：自然科学版.2010,34(5)：642-648页
[118]刘华山,朱世强,王宣银.扭矩输入有界的机器人模糊PD轨迹跟踪[J].电机与控制学报.2010,14(1)：78-83页
[119]吴伟,刘兴刚,王忠实,et al.多传感器融合实现机器人精确定位[J].东北大学学报(自然科学版).2007,28(2)：161-164页
[120]吴皓,田国会,陈西博,et al.基于机器人服务任务导向的室内未知环境地图构建[J].机器人.2010,32(2)：196-203页
[121]昕马,锐宋,睿郭,et al.基于免疫自适应遗传算法的机器人栅格地图融合[J].控制理论与应用.2009,26(9)：1004-1008页
[122]熊蓉,褚健,吴俊,et al.基于点线相合的机器人增量式地图构建[J].控制理论与应用.2007,24(2)：170-176页
[123]Lee K, Doh N L, Chung W K, et al. A robust localization algorithm in topological maps with dynamic noises[J]. Industrial Robot.2008,35(5):435-448P
[124]Blanco J L, Gonzalez J, Fernandez-Madrigal J A. Subjective local maps for hybrid metric-topological SLAM[J]. Robotics and Autonomous Systems.2009,57(1):64-74 P
[125]Shi C, Wang Y, Yang J. Online topological map building and qualitative localization in large-scale environment[J]. Robotics and Autonomous Systems.2010,58(5):488-496 P
[126]Berrada M, Badran F, Crepon M, et al. A global optimization method using a random walk on a topological map and local variational inversions [J]. Inverse Problems.2010, 26(12):408-416P
[2]孟彦鹏,王永,谢圆,et al.基于Creator/Vega的月球车轮地交互仿真[J].机器人.2010,32(3)：369-374页
[3]陈勇,桂卫华,王随平.深海采矿机器人控制体系结构研究[J].控制工程.2009,16(4)：488-490页
[4]Salichs M A, Moreno L. Navigation of mobile robots:Open questions[J]. Robotica. 2000,18(3):227-234页
[5]王璐.未知环境中移动机器人视觉环境建模与定位研究[D].中南大学博士学位论文,2007
[6]Davison A J, Murray D W. Simultaneous localization and map-building using active vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(7): 865-880P
[7]Davison A J, Reid I D, Molton N D, et al. MonoSLAM:Real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007,29(6): 1052-1067P
[8]Eade E, Drummond T. Edge landmarks in monocular SLAM[J]. Image and Vision Computing.2009,27(5):588-596P
[9]Pinies P, Tardos J D. Large-scale SLAM building conditionally independent local maps: Application to monocular vision[J]. IEEE Transactions on Robotics.2008,24(5): 1094-1106P
[10]Cheein F A, Scaglia G, Di Sciasio F, et al. Feature selection criteria for real time EKF-SLAM algorithm[J]. International Journal of Advanced Robotic Systems.2010, 7(2):115-124P
[11]赵立坤,武二永,郭羰平,et al.基于概率选取随机特征点的单目视觉SLAM方法[J].机器人.2010,32(05)：642-646页
[12]许俊勇,王景川,陈卫东.基于全景视觉的移动机器人同步定位与地图创建研究[J].机器人.2008,30(4)：289-297页.
[13]高明.基于全景视觉的单目SLAM系统[D].合肥工业大学硕士学位论文,2009
[14]Cheein F A, Scaglia G, Di Sciasio F, et al. Feature selection criteria for real time EKF-SLAM algorithm[J]. International Journal of Advanced Robotic Systems.2010, 7(2):115-124P
[15]Gil A, Reinoso O, Ballesta M, et al. Multi-robot visual SLAM using a Rao-Blackwellized particle filter[J]. Robotics and Autonomous Systems.2010,58(1): 68-80P
[16]陈凤东,洪炳镕.一种基于图像的移动机器人泊位方法[J].机器人.2010,32(2)：166-170页
[17]Hong J, Tan X, Pinette B, et al. Image-based homing[J]. IEEE Control Systems Magazine.1992,12(1):38-45P
[18]陆军,孙凌丽,穆海军,et al.基于全景视觉的机器人相互定位的研究[J].哈尔滨工程大学学报.2010,31(4)：457-464页
[19]Gro R, Bonani M, Mondada F, et al. Autonomous self-assembly in swarm-bots[J]. IEEE Transactions on Robotics.2006,22(6):1115-1130P
[20]Franz M O, Scholkopf B, Mallot H A, et al. Where did I take that snapshot? Scene-based homing by image matching[J]. Biological Cybernetics.1998,79(3):191P
[21]张帆.全景视觉图像质量优化方法研究[D].哈尔滨工程大学博士学位论文,2010
[22]工海军.未知环境下移动机器人即时定位与地图创建[D].上海大学博士学位论文,2009
[23]石朝侠,洪炳镕,周彤,et al.大规模环境下的拓扑地图创建与导航[J].机器人2007,29(5)：433-438页
[24]Wetherbie Iii J O, Smith C E. Large-scale feature identification for indoor topological mapping[C]. Tucson, AZ, United states:2001
[25]庄严,徐晓东,王伟.移动机器人几何-拓扑混合地图的构建及自定位研究[J].控制与决策.2005,20(07)：815-822页
[26]司秉玉.基于可视人工路标的自主机器人导航若干问题研究[D].东北大学博士学位论文,2003
[27]Becker C, Salas J, Tokusei K, et al. Reliable navigation using landmarks[C]. Nagoya, Jpn: 1995
[28]Taylor C J, Kriegman D J. Vision-based motion planning and exploration algorithms for mobile robots[J]. IEEE Transactions on Robotics and Automation.1998,14(3): 417-426P
[29]Zitova B, Flusser J. Landmark recognition using invariant features[J]. Pattern Recognition Letters.1999,20(5):541-547P
[30]胡英,赵姝颖,徐心和.色标设计与辨识算法研究[J].中国图象图形学报.2002,7(12)：1291-1295页
[31]董再励,郝颖明,朱枫.一种基于视觉的移动机器人定位系统[J].中国图象图形学报.2000(08)：687-692页
[32]沙超,王汝传,孙力娟,et al.无线传感器网络中一种信标节点可迁移的协作定位方法[J].电子学报.2010,38(11)：2625-2629页
[33]孙光民,王晶,于光宇,et al.自然背景中交通标志的检测与识别[J].北京工业大学学报.2010,36(10)：1337-1343页
[34]李伦波,马广富.自然场景下交通标志检测与分类算法研究[J].哈尔滨工业大学学报.2009,41(11)：29-38页
[35]Desouza G N, Kak A C. Vision for mobile robot navigation:A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(2):237-267P
[36]Kosaka A, Kak A C. Fast vision-guided mobile robot navigation using model-based reasoning and prediction of uncertainties[J]. CVGIP: Image Understanding.1992,56(3): 271-329P
[37]严永杰.多机器人系统协调与控制研究[D].哈尔滨工程大学博士学位论文,2007
[38]Argyros A A, Bekris K E, Orphanoudakis S C, et al. Robot homing by exploiting panoramic vision[J]. Autonomous Robots.2005,19(1):7-25P
[39]Se S, Lowe D G, Little J J. Vision-based global localization and mapping for mobile robots[J]. IEEE Transactions on Robotics.2005,21(3):364-375P
[40]Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision.2000,37(2):151-172P
[41]Mikolajczyk K, Schmid C. Scale affine invariant interest point detectors [J]. International Journal of Computer Vision.2004,60(1):63-86P
[42]雷明.图像特征的检测、描述及匹配[D].重庆大学硕士学位论文,2008
[43]C Harris M S. A combined corner and edge detector[Z]. Mancheste:1988,147-151P
[44]Mikolajzyk K. Detection of local features invariant to affine transformations[D]. Institut National Polytechnique de Grenoble,2002
[45]王永明,王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社,2010：203
[46]Mikolajczyk K, Leibe B, Schiele B. Local features for object class recognition[C]. Beijing, China:2005
[47]Lowe D G. Object recognition from local scale-invariant features[C]. Kerkyra, Greece: 1999
[48]Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision.2004,60(2):91-110P
[49]Lindeberg T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision.1998,30(2):79-116P
[50]Bay H, Ess A, Tuytelaars T, et al. Speeded-Up Robust Features (SURF)[J]. Computer Vision and Image Understanding.2008,110(3):346-359P
[51]徐秀云.基于特征点的景象匹配技术研究[D].南京理工大学硕士学位论文,2009
[52]Matas J, Chum O, Urban M, et al. Robust wide-baseline stereo from maximally stable extremal regions[C].2004
[53]Tuytelaars T, Van Gool L. Matching widely separated views based on affine invariant regions[J]. International Journal of Computer Vision.2004,59(1):61-85P
[54]Tuytelaars T, Van Gool L. Wide baseline stereo matching based on local, affinely invariant regions[J].2000
[55]Kadir T, Brady M. Saliency, scale and image description[J]. International Journal of Computer Vision.2001,45(2):83-105P
[56]Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[C]. Madison, WI, United states:2003
[57]Ke Y, Sukthankar R. PCA-SIFT:A more distinctive representation for local image descriptors[C]. Washington, DC, United states:2004
[58]Belongie S, Malik J, Puzicha J. Shape context:A new descriptor for shape matching and object recognition[Z].2000,831-837P
[59]Koenderink J J, Doom A V. Representation of local geometry in the visual system[J]. Biological Cybernetics.1987,6(55):367-375P
[60]Van G L, Moons T, Ungureanu D. Affine/photometric invariants for planar intensity patterns[C]. Cambridge, United kingdom:1996
[61]万玮,冯学智,肖鹏峰,et al.基于傅里叶描述子的高分辨率遥感图像地物形状特征表达[J].遥感学报.2011,15(01)：73-87页
[62]封筠,穆志纯,毛晚堆.基于局部二值模式与滤波器融合的人耳识别[J].计算机工程与应用.2010,46(35)：192-195页
[63]Bowyer K, Kranenburg C, Dougherty S. Edge detector evaluation using empirical ROC curves [J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1999,1:354-359P
[64]Heath M, Sarkar S, Sanocki T, et al. Comparison of edge detectors. A methodology and initial study[J]. Computer Vision and Image Understanding.1998,69(1):38-54P
[65]Lopez A M, Lumbreras F, Serrat J, et al. Evaluation of methods for ridge and valley detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1999, 21(4):327-335P
[66]Brand P, Mohr R. Accuracy in image measure[C]. Boston, MA, USA:1994
[67]Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision.2000,37(2):151-172P
[68]李雷达,郭宝龙,表金峰.基于奇偶量化的空域抗几何攻击图像水印算法[J].电子与信息学报.2009,31(01)：134-138页
[69]徐紫涵,王向阳.可有效抵抗一般性几何攻击的数字水印检测方法[J].自动化学报.2009,35(01)：23-27页
[70]朱海峰,赵春晖.图像特征点分布均匀性的评价方法[J].大庆师范学院学报.2010,30(03)：9-12页
[71]Morris R G M. Spatial Localization Does Not Require the Presence of Local Cues[J]. Learning and Motivation.1981,2(12):239-260P
[72]Cartwright B A, Collett T S. Landmark maps for honeybees [J]. Biological Cybernetics. 1987,57(1-2):85-93P
[73]Cartwright B A, Collett T S C. Landmark learning in bees[J]. Journal of Comparative Physiology.1983,151:521-543P
[74]Wehner R. The desert ant's navigational toolkit: Procedural rather than positional knowledge[C].3975 University Drive, Suite 390, Fairfax, VA 22030, United States: 2008
[75]Knaden M, Wehner R. Path integration in desert ants controls aggressiveness[J]. Science. 2004,305(5680):60P
[76]Muller M, Wehner R. Path integration in desert ants, Cataglyphis fortis[J]. Proceedings of the National Academy of Sciences.1988,85(14):5287-5290P
[77]Judd S P D, Collett T S. Multiple stored views and landmark guidance in ants[J]. Nature. 1998,392(6677):710-714P
[78]Collett T S. Insect navigation en route to the goal:Multiple strategies for the use of landmarks[J]. Journal of Experimental Biology.1996,199:227-235P
[79]Horridge A. Pattern and 3d vision of insects [J]. In Visual Navigation.1997:26-59P
[80]Wehner R, Michel B, Antonsen P. Visual navigation in insects:Coupling of egocentric and geocentric information[J]. Journal of Experimental Biology.1996,199:129-140
[81]Rofer T, Ofer T R. Controlling a Wheelchair with Image-based Homing[C].1997
[82]Lambrinos D, Moller R, Labhart T, et al. Mobile robot employing insect strategies for navigation[J]. Robotics and Autonomous Systems.2000,30(1):39-64P
[83]Moller R. Insect visual homing strategies in a robot with analog processing[J]. Biological Cybernetics.2000,83(3):231-243P
[84]Gaussier P, Joulain C, Banquet J P, et al. The visual homing problem:An example of robotics/biology cross fertilization[J]. Robotics and Autonomous Systems.2000,30(1-2): 155-180P
[85]Basten K, Mallot H A. Simulated visual homing in desert ant natural environments: Efficiency of skyline cues[J]. Biological Cybernetics.2010,102(5):413-425P
[86]Franz M O, Scholkopf B, Mallot H A, et al. Where did I take that snapshot? Scene-based homing by image matching[J]. Biological Cybernetics.1998,79(3):191P
[87]Zeil J, Hofmann M I, Chahl J S. Catchment areas of panoramic snapshots in outdoor scenes[J]. Journal of the Optical Society of America A: Optics and Image Science, and Vision.2003,20(3):450-469P
[88]Binding D, Binding D, Labrosse F, et al. Visual local navigation using warped panoramic images[C].2006
[89]Sturzl W, Mallot H A. Efficient visual homing based on Fourier transformed panoramic images[J]. Robotics and Autonomous Systems.2006,54(4):300-313P
[90]郑重.非结构环境下的移动机器人路径规划算法研究[D].中国科学技术大学博士学位论文,2009
[91]Chunlin T, Hongqiao W, Deli P. SWF-SIFT Approach for Infrared Face Recognition[J]. Tsinghua Science and Technology.2010,15(03):357-362P
[92]Zhu Q, Li Ke. Image stitching using simplified SIFT[C]. Harbin, Heilongjiang, China: 2010
[93]关洪洋.图像融合与配准技术在掌纹图像中的应用[D].吉林大学硕士学位论文,2010
[94]Rao-Blackwellized滤波器实现机器人同时定位和地图创建[J].哈尔滨工业大学学报.2008,40(03)：401-406页
[95]Mikolajczyk K, Schmid C. Scale affine invariant interest point detectors[J]. International Journal of Computer Vision.2004,60(1):63-86P
[96]Wang Y, Lin M, Ju R, et al. Image feature initialization for SLAM and moving object detection[J]. ICIC Express Letters.2009,3(3):477-482P
[97]Li S, Chen T, Yu C, et al. SURF-based video mosaic and its key technologies[J]. Journal of Computational Information Systems.2010,6(10):3267-3276P
[98]An M, Jiang Z, Zhao D. High speed robust image registration and localization using optimized algorithm and its performances evaluation[J]. Journal of Systems Engineering and Electronics.2010,21(3):520-526P
[99]雷兰一菲,郎海涛.几种典型局部图像特征的比较[J].计算机应用.2010,30(S2)：50-53页
[100]Gil A, Mozos O M, Ballesta M, et al. A comparative evaluation of interest point detectors and local descriptors for visual SLAM[J]. Machine Vision and Applications. 2010,21(6):905-920P
[101]Rochdi B, Kamel B. Comparative study of interest point detectors and descriptors for automatic remote-sensing image registration[J]. International Review on Computers and Software.2010,5(3):264-275P
[102]熊智,陈方,王丹,et al.SAR/INS组合导航中基于SURF的鲁棒景象匹配算法[J].南京航空航天大学学报.2011,43(01)：49-54页
[103]谭正华,王李管,陈建宏,et al.基于KD树的露天矿采场示坡线自动生成方法[J].计算机应用.2010,30(07)：1840-1938页
[104]潘章明.一种基于KD树子样的自动聚类方法[J].计算机工程与科学.2011,33(01)：166-170页
[105]贾广利,魏娟,马宏伟.一种六履带侦查机器人的运动分析及结构设计[J].机床与液压.2008,36(11)：8-10页
[106]滕赞,姚辰,王挺,et al.变形履带轮椅机器人的张紧力最优估计和越障能力分析[J].机器人.2010,32(5)：622-629页
[107]李允旺,葛世荣,朱华.摇杆式履带悬架的构型推衍及其在煤矿救灾机器人上的应用[J].机器人.2010(1)：25-33页
[108]Dean A J, Brennan S N. A low-order dynamic model of a tracked robot inclusive of non-linear slip[J].International Journal of Heavy Vehicle Systems.2008,15(2-4): 327-355P
[109]孙自广,李春贵,王秦.基于改进遗传算法的机器人路径规划[J].自动化与仪表.2009,24(6)：5-7页
[110]陶敏,陈新,孙振平.移动机器人定位技术[J].火力与指挥控制.2010,35(7)：169-172页
[111]白冰洋,沈阳.推算定位算法在拦截策略中的研究与应用[J].计算机仿真.2009,26(3)：169-171页
[112]Bevly D M, Parkinson B. Cascaded Kalman filters for accurate estimation of multiple biases, dead-reckoning navigation, and full state feedback control of ground vehicles[J]. IEEE Transactions on Control Systems Technology.2007,15(2):199-208P
[113]Azenha A, Carvalho A. Dynamic analysis of AGV control under dead-reckoning algorithm[J]. Robotica.2008,26(5):635-641P
[114]温素芳.基于模糊控制的移动机器人动态避碰的研究[D].哈尔滨工程大学硕士学位论文,2005
[115]蔡建羡,阮晓钢,郜园园.随机模糊控制策略及其在机器人控制中的应用[J].电机与控制学报.2009,13(5)：754-761页
[116]徐国政,宋爱国,李会军.基于模糊逻辑的上肢康复机器人阻抗控制实验研究[J].机器人.2010,32(6)：792-798页
[117]康亮,赵春霞,郭剑辉.基于模糊滚动RRT算法的移动机器人路径规划[J].南京理工大学学报：自然科学版.2010,34(5)：642-648页
[118]刘华山,朱世强,王宣银.扭矩输入有界的机器人模糊PD轨迹跟踪[J].电机与控制学报.2010,14(1)：78-83页
[119]吴伟,刘兴刚,王忠实,et al.多传感器融合实现机器人精确定位[J].东北大学学报(自然科学版).2007,28(2)：161-164页
[120]吴皓,田国会,陈西博,et al.基于机器人服务任务导向的室内未知环境地图构建[J].机器人.2010,32(2)：196-203页
[121]昕马,锐宋,睿郭,et al.基于免疫自适应遗传算法的机器人栅格地图融合[J].控制理论与应用.2009,26(9)：1004-1008页
[122]熊蓉,褚健,吴俊,et al.基于点线相合的机器人增量式地图构建[J].控制理论与应用.2007,24(2)：170-176页
[123]Lee K, Doh N L, Chung W K, et al. A robust localization algorithm in topological maps with dynamic noises[J]. Industrial Robot.2008,35(5):435-448P
[124]Blanco J L, Gonzalez J, Fernandez-Madrigal J A. Subjective local maps for hybrid metric-topological SLAM[J]. Robotics and Autonomous Systems.2009,57(1):64-74 P
[125]Shi C, Wang Y, Yang J. Online topological map building and qualitative localization in large-scale environment[J]. Robotics and Autonomous Systems.2010,58(5):488-496 P
[126]Berrada M, Badran F, Crepon M, et al. A global optimization method using a random walk on a topological map and local variational inversions [J]. Inverse Problems.2010, 26(12):408-416P
© 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 |