面向虚拟现实飞行模拟训练的视觉手交互技术研究
|
摘要
飞行模拟器是一种能逼真模拟真实飞机在空中以及地面运动的航空试验设备。南京航空航天大学飞行模拟与先进培训工程技术研究中心于21世纪伊始便致力于基于虚拟现实技术的飞行模拟器的研究，并提出了半虚拟现实座舱的概念。舱内的操作设备采用实物提供力觉和触觉反馈，舱内及舱外的视景由计算机生成并输出到头盔显示器。但在半虚拟现实座舱中还需采用适当的方式，将手作为视觉反馈提供给用户，而传统的数据手套容易产生约束感和异物感，影响人的沉浸感。为此，本文采用更能体现“以人为中心”的基于视觉的交互方案，通过计算机视觉技术对用户的手势进行跟踪和识别，然后利用获得的数据驱动手模型，实现半虚拟现实座舱中虚拟手的可视化。此外，本文将计算机视觉技术应用于桌面虚拟现实训练系统，作为培训飞行员的一种补充手段。文中主要研究内容可概括如下：
（1）手势特征提取以及多特征融合。针对半虚拟现实座舱这种特殊的应用环境，舱内操作设备对操作手势存在一定的约束形式，即操作设备的外形及位置基本决定了操作手势的类别和姿态，因此采用基于表观的手姿态估计方法。通过对手势图像库提取特征，建立手势特征与姿态参数间的映射，将姿态估计问题转换为特征检索问题。使用手势分割、轮廓搜寻、轮廓平滑和肤色填充四个步骤对手势图像进行预处理。对预处理后的手势图像，提出形状特征和颜色特征相结合的特征提取方法，其中形状特征采用梯度方向直方图（Histogram of Oriented Gradient，HOG）特征，颜色特征采用色度直方图特征，并根据特征相似性度量下的检索评价准则，确定形状特征和颜色特征在融合过程中各自所占的融合权重。
（2）大容量高维度的手势特征检索。为提高手势特征的检索速度并克服“维数灾难”问题，使用局部敏感哈希（Locality Sensitive Hashing，LSH）索引方法进行近似近邻检索。为避免LSH索引建立的哈希表超出计算机的内存范围，采用多探测原理对多个哈希桶进行探测，加大库中特征与查询特征在单张哈希表中发生碰撞的概率。同时，为进一步提高算法的时间效率，引入近邻特征表，使用耗时较少的查询操作代替部分欧氏距离的计算。根据以上两点，提出了改进的LSH索引方法。此外，为优化改进LSH中的索引参数，提出了索引性能预测模型。本文实验表明，该预测模型能够反映实际的索引性能，利用优化参数后的改进LSH索引进行10–近邻特征检索，能以索引召回率下降3%为代价，将在线实际耗时减少41.9%。
（3）自遮挡情况下的手姿态估计。针对手在半虚拟现实座舱中操作所遇到的自遮挡问题，引入多个视点下的手势图像。为避免多视点下的手势图像库容量过分增加，建立手势特征树，提出了在最大后验概率（Maximum a Posteriori，MAP）框架下，通过特征树节点搜索保证概率意义上的姿态最优解，并利用时序一致加权提高姿态估计精度。本文实验表明，通过建立手势特征树，可以将手姿态估计速度从4.4帧/s的提高至8.2帧/s，并且在自遮挡情况下仍能有效地估计手指关节参数以及手腕姿态参数，能够满足用户与半虚拟现实座舱之间的交互需求。
（4）指尖检测、定位和手势识别。针对桌面虚拟现实训练系统，实现基于视觉的接触式和非接触式两种训练方式。接触式训练中，对手部进行实时跟踪和定位，计算手指指尖的三维位置，实现真实手与虚拟物体的精细碰撞检测。其中，提出了使用指甲盖标记与轮廓凸缺陷分析相结合的方法检测手指指尖，并提出了引入深度信息的对偶正交摄像机系统及坐标值轮流逼近定位算法计算指尖的三维空间位置。本文实验表明，该算法对指尖的平均定位误差小于0.1cm。非接触式训练中，提出了基于分层时序记忆（Hierarchical Temporal Memory，HTM）的手势识别方法，识别飞行模拟过程中的各种操作手势，所述方法对10种静态手势的识别率超过90%。同时，结合指尖定位结果作为各种操作的输入控制量，实现用户只使用手势即完成飞行模拟的全过程。
Flight simulator is an aviation equipment that can simulate airplane’s movement in air andground realistically. It is a typical application of system simulation technology and virtual realitytechnology which is widely used in civil aviation and military aviation areas. Since the beginning of21th century, the Flight Simulation and Advanced Training Engineering Technology Research Centerof Nanjing University of Aeronautics and Astronautics has been concentrated on the study of flightsimulator based on virtual reality technology and proposed the concept of semi-virtual reality cockpitin which the force and tectile sense are provided by real operation equipments and the visual sense isgenerated by HMD (Helmet-Mounted Display). The system also needs an appropriate way to providethe visual feedback of user’s hand, but it will affect immersion sense and destroy the naturalness andconcordance in interaction if traditional CyberGlove is used. Therefore, this paper adopts aninteractive scheme based on hand pose estimation to visualize the virtual hands. In addition, computervision technology is also applied to desktop virtual reality training system as a complementaryprocedure of training pilots. The main research contents are summarized as follows:
1. Gesture features extraction and fusion. The gestures are constrained by the equipments insemi-virtual reality cockpit. In other words, the category of gesture and pose of hand are determinedby the shapes and positions of the equipments. An appearance-based method of hand pose estimationis utilized in this paper, which converts hand tracking problem into a hand pose indexing problem byconstructing gesture image database and creating a mapping between gesture features and hand poses.Before gesture features extraction, image preprocessing which contains hand segmentation, contoursearching, contour smoothing and skin filling is performed. Then the HOG (Histogram of OrientedGradient) features and chromaticity histogram features are fused using evaluation of retrievalprecision to identify the fusion weights.
2. Large-capacity and high-dimension feature indexing. In order to improve retrieval speed andsolve the “Curse of Dimensionality” problem, an improved LSH (Locality Sensitive Hashing) methodis proposed in this paper. And a predictive model is built to evaluate the index parameters. Thesimulation results show that the predictive model is appropriate to the practical index performanceand the time consumption could be reduced by41.9%at the cost of the recall rate drop3%for10-NN(Nearest Neighbors) retrieval.
3. Hand pose estimation under self-occlusion. According to hand self-occlusion insemi-virtual reality cockpit, multi-view gesture databases are introduced. In order to avoid capacity in databases increase excessively, a tree model is constructed using multi-view gesture features. UnderMAP (Maximum a Posteriori) framework, tree node searching is used to ensure the pose estimation isoptimal in probabilistic sense. Besides, the estimation results are weighted by temporal consistencywhich could enhance the accuracy. Experimental results show that the speed of the proposed methodcould be increased from4.4fps to8.2fps, and the poses of finger and wrist could also be estimatedaccurately.
4. Fingertip detection, position and gesture recognition. According to the Desktop Virtual RealitySystem, contact and non-contact training methods are accomplished in this paper. The contact trainingmethod uses fingertip detection and position algorithms to judge the collision between real hand andvirtual objects. Fingertip detection is realized by combining mark identification and convexity defectsanalysis, and dual orthogonal camera system with image depth information is proposed to implementthe fingertip position. Experimental results show that the average accuracy of position could be asgood as0.1cm. In non-contact training, a gesture recognition method based HTM (HierarchicalTemporal Memory) network which is inspired by vision system of mammal is proposed. Recognitionrate of the proposed method is higher than90%against10kinds of gesture. Combining the gesturerecognition and fingertip position, a pilot could complete the whole process of flight simulation onlyutilize movement gestures.
（1）手势特征提取以及多特征融合。针对半虚拟现实座舱这种特殊的应用环境，舱内操作设备对操作手势存在一定的约束形式，即操作设备的外形及位置基本决定了操作手势的类别和姿态，因此采用基于表观的手姿态估计方法。通过对手势图像库提取特征，建立手势特征与姿态参数间的映射，将姿态估计问题转换为特征检索问题。使用手势分割、轮廓搜寻、轮廓平滑和肤色填充四个步骤对手势图像进行预处理。对预处理后的手势图像，提出形状特征和颜色特征相结合的特征提取方法，其中形状特征采用梯度方向直方图（Histogram of Oriented Gradient，HOG）特征，颜色特征采用色度直方图特征，并根据特征相似性度量下的检索评价准则，确定形状特征和颜色特征在融合过程中各自所占的融合权重。
（2）大容量高维度的手势特征检索。为提高手势特征的检索速度并克服“维数灾难”问题，使用局部敏感哈希（Locality Sensitive Hashing，LSH）索引方法进行近似近邻检索。为避免LSH索引建立的哈希表超出计算机的内存范围，采用多探测原理对多个哈希桶进行探测，加大库中特征与查询特征在单张哈希表中发生碰撞的概率。同时，为进一步提高算法的时间效率，引入近邻特征表，使用耗时较少的查询操作代替部分欧氏距离的计算。根据以上两点，提出了改进的LSH索引方法。此外，为优化改进LSH中的索引参数，提出了索引性能预测模型。本文实验表明，该预测模型能够反映实际的索引性能，利用优化参数后的改进LSH索引进行10–近邻特征检索，能以索引召回率下降3%为代价，将在线实际耗时减少41.9%。
（3）自遮挡情况下的手姿态估计。针对手在半虚拟现实座舱中操作所遇到的自遮挡问题，引入多个视点下的手势图像。为避免多视点下的手势图像库容量过分增加，建立手势特征树，提出了在最大后验概率（Maximum a Posteriori，MAP）框架下，通过特征树节点搜索保证概率意义上的姿态最优解，并利用时序一致加权提高姿态估计精度。本文实验表明，通过建立手势特征树，可以将手姿态估计速度从4.4帧/s的提高至8.2帧/s，并且在自遮挡情况下仍能有效地估计手指关节参数以及手腕姿态参数，能够满足用户与半虚拟现实座舱之间的交互需求。
（4）指尖检测、定位和手势识别。针对桌面虚拟现实训练系统，实现基于视觉的接触式和非接触式两种训练方式。接触式训练中，对手部进行实时跟踪和定位，计算手指指尖的三维位置，实现真实手与虚拟物体的精细碰撞检测。其中，提出了使用指甲盖标记与轮廓凸缺陷分析相结合的方法检测手指指尖，并提出了引入深度信息的对偶正交摄像机系统及坐标值轮流逼近定位算法计算指尖的三维空间位置。本文实验表明，该算法对指尖的平均定位误差小于0.1cm。非接触式训练中，提出了基于分层时序记忆（Hierarchical Temporal Memory，HTM）的手势识别方法，识别飞行模拟过程中的各种操作手势，所述方法对10种静态手势的识别率超过90%。同时，结合指尖定位结果作为各种操作的输入控制量，实现用户只使用手势即完成飞行模拟的全过程。
Flight simulator is an aviation equipment that can simulate airplane’s movement in air andground realistically. It is a typical application of system simulation technology and virtual realitytechnology which is widely used in civil aviation and military aviation areas. Since the beginning of21th century, the Flight Simulation and Advanced Training Engineering Technology Research Centerof Nanjing University of Aeronautics and Astronautics has been concentrated on the study of flightsimulator based on virtual reality technology and proposed the concept of semi-virtual reality cockpitin which the force and tectile sense are provided by real operation equipments and the visual sense isgenerated by HMD (Helmet-Mounted Display). The system also needs an appropriate way to providethe visual feedback of user’s hand, but it will affect immersion sense and destroy the naturalness andconcordance in interaction if traditional CyberGlove is used. Therefore, this paper adopts aninteractive scheme based on hand pose estimation to visualize the virtual hands. In addition, computervision technology is also applied to desktop virtual reality training system as a complementaryprocedure of training pilots. The main research contents are summarized as follows:
1. Gesture features extraction and fusion. The gestures are constrained by the equipments insemi-virtual reality cockpit. In other words, the category of gesture and pose of hand are determinedby the shapes and positions of the equipments. An appearance-based method of hand pose estimationis utilized in this paper, which converts hand tracking problem into a hand pose indexing problem byconstructing gesture image database and creating a mapping between gesture features and hand poses.Before gesture features extraction, image preprocessing which contains hand segmentation, contoursearching, contour smoothing and skin filling is performed. Then the HOG (Histogram of OrientedGradient) features and chromaticity histogram features are fused using evaluation of retrievalprecision to identify the fusion weights.
2. Large-capacity and high-dimension feature indexing. In order to improve retrieval speed andsolve the “Curse of Dimensionality” problem, an improved LSH (Locality Sensitive Hashing) methodis proposed in this paper. And a predictive model is built to evaluate the index parameters. Thesimulation results show that the predictive model is appropriate to the practical index performanceand the time consumption could be reduced by41.9%at the cost of the recall rate drop3%for10-NN(Nearest Neighbors) retrieval.
3. Hand pose estimation under self-occlusion. According to hand self-occlusion insemi-virtual reality cockpit, multi-view gesture databases are introduced. In order to avoid capacity in databases increase excessively, a tree model is constructed using multi-view gesture features. UnderMAP (Maximum a Posteriori) framework, tree node searching is used to ensure the pose estimation isoptimal in probabilistic sense. Besides, the estimation results are weighted by temporal consistencywhich could enhance the accuracy. Experimental results show that the speed of the proposed methodcould be increased from4.4fps to8.2fps, and the poses of finger and wrist could also be estimatedaccurately.
4. Fingertip detection, position and gesture recognition. According to the Desktop Virtual RealitySystem, contact and non-contact training methods are accomplished in this paper. The contact trainingmethod uses fingertip detection and position algorithms to judge the collision between real hand andvirtual objects. Fingertip detection is realized by combining mark identification and convexity defectsanalysis, and dual orthogonal camera system with image depth information is proposed to implementthe fingertip position. Experimental results show that the average accuracy of position could be asgood as0.1cm. In non-contact training, a gesture recognition method based HTM (HierarchicalTemporal Memory) network which is inspired by vision system of mammal is proposed. Recognitionrate of the proposed method is higher than90%against10kinds of gesture. Combining the gesturerecognition and fingertip position, a pilot could complete the whole process of flight simulation onlyutilize movement gestures.
引文
[1] Burdea G, Coiffet P. Virtual reality technology. New York: John Wiley&Sons,1994.
[2] Sturman D J, Zeltzer D. A survey of glove-based input. IEEE Transaction on Computer Graphicsand Applications,1994,14(1):30-39.
[3]任程,戴树岭.基于数据手套的逼真虚拟手的实现.系统仿真学报,2008,20(22):6214-6217.
[4]宿春慧,杨方廷,涂颖.基于数据手套虚拟训练系统的研究与实现.系统仿真学报,2009,10(21):189-192.
[5] Livingston M A, State A. Magnetic tracker calibration for improved augmented realityregistration. Teleoperators and Virtual Environments,1997,6(5):532-546.
[6] Gu H B, Wu D S, Liu H. Development of a novel low-cost flight simulator for pilot training.World Academy of Science, Engineering and Technology,2009,60:685-689.
[7]罗斌,姚鹏,翁冬冬,等.基于混合现实的新型轻量级飞行模拟器系统.系统仿真学报,2009,21(17):5406-5410.
[8] Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computerinteraction: a review. Pattern Analysis and Machine Intelligence,1997,19(7):677-695.
[9] Kuch J J. Vision-based hand modeling and gesture recognition for human computer interaction.Master’s Thesis, Univ. of Illinois at Urbana-Champaign,1994.
[10] Regh J M, Kanade T. DigitEyes: vision-based hand tracking for human-computer interaction.Motion of Non-Rigid and Articulated Objects,1994:16-22.
[11]梁路宏,艾海舟,徐光祐,等.人脸检测研究综述.计算机学报,2002,25(5):449-458.
[12] Rehg J, Kanade T. Visual tracking of self-occluding articulated objects. Technical ReportCMU-CS-94-224, Carnegie Mellon University,1994.
[13] Lathuiliere F, Herve J Y. Visual hand posture tracking in a gripper guiding application. IEEEInternational Conference Robotics and Automation, San Francisco, USA, April:24-28,2000:1688-1694.
[14] Lee J, Kunii T L. Model-based analysis of hand posture. Computer Graphics and Applications,1995,15(5):77-86.
[15] Sasaki A, Yolota S, Ohyama Y. Hand pose estimation from camera images of ring-shapedmarkers. ICCAS-SICE, Fukuoka, Japan, Aug.18-21,2009:3255-3259.
[16] Usabiaga J, Erol A, Bebis G, et al. Global hand pose estimation by multiple camera ellipsetracking. Advances in Visual Computing.2006,4291(2006):122-132.
[17] Zappi V, Brogni A, Caldwell D. Passive hand pose recognition in virtual reality. IEEESymposium on3D User Interfaces, Westin Waltham-Boston, USA, March20-212010:143-144.
[18] Koike H, Sato Y, Kobayashi Y. Integrating paper and digital information on EnhancedDesk: amethod for realtime finger tracking on an augmented desk system. ACM Transactions onComputer-Human Interaction,2001,8(4):307-322.
[19]杨端端,金连文,尹俊勋.手指书写汉字识别系统中的指尖检测方法.华南理工大学学报:自然科学版,2007,35(1):58-63.
[20] Segen J, Kumar S. Gesture VR: vision-based3d hand interace for spatial interaction. ACMInternational Conference on Multimedia, Bristol, UK, September12-16,1998:455-464.
[21] Wu A, Shah M, Da V. A virtual3D blackboard:3D finger tracking using a single camera.International Conference on Automatic Face and Gesture Recognition,2000:536-543.
[22] Caglar M B, Lobo N. Open hand detection in a cluttered single image using finger primitives.Computer Vision and Pattern Recognition Workshop, June17-22,2006:148-153.
[23]梅萍华,李斌,朱中的,等.基于径向对称变换的实时指尖检测算法.中国科学技术大学学报,2011,41(2):101-107.
[24] Rehg J, Kanade T. Visual tracking of high dof articulated structures: an application to humanhand tracking. Lecture Notes in Computer Science,1994,801(1994):35-46.
[25] Wu Y, Huang T S. Capturing articulated human hand motion: a divide-and-conquer approach.IEEE International Conference on Computer Vision, Kerkyra, Greece, September20-27,1999:606-611.
[26] Wu Y, Lin J Y, Huang T S. Capturing natural hand articulation. IEEE International Conferenceon Computer Vision, Vancouver, Canada, July7-14,2001:426-432.
[27] Lin J Y, Wu Y, Huang T S. Capturing human hand motion in image sequences. Workshop onMotion and Video Computing, Dec5-6,2002:99-104.
[28] Heap T, Hogg D. Towards3D hand tracking using a deformable model. International Conferenceon Automatic Face and Gesture Recognition, Killington, USA, Oct.14-16,1996:140-145.
[29] Zhou H, Huang T S. Tracking articulated hand motion with eigen dynamics analysisl. IEEEInternational Conference on Computer Vision, Nice, France, Oct.13-16,2003:1102-1109.
[30] Bray M, Koller-Meier E, Muller P, et al.3D hand tracking by rapid stochastic gradient descentusing a skinning model. European Conference on Visual Media Production, March15-16,2004:59-68.
[31] Bray M, Koller-Meier E, Gool L V. Smart particle filtering for high-dimensional tracking.Computer Vision and Image Understanding,2007,106(1):116-129.
[32] Lien C C. A scalable model-based hand posture analysis system. Machine Vision andApplications,2005,16(3):157-169.
[33] Rehg J M, Kanade T. Model-based tracking of self-occluding articulated objects. InternationalConference on Computer Vision, Cambridge, MA, USA, Jun.20-23,1995:612-617.
[34] Athitsos V, Sclaroff S.3D hand pose estimation by finding appearance-based matches in a largedatabase of training views. IEEE Workshop on Cues in Communication, Kauai, Hawaii, USA,December9,2001.
[35] Athitsos V, Sclaroff S. An appearance-based framework for3D hand shape classification andcamera viewpoint estimation. IEEE International Conference on Automatic Face and GestureRecognition, Washington, USA, May20-21,2002:40-45.
[36] Athitsos V, Sclaroff S. Database indexing methods for3D hand pose estimation. Gesture-BasedCommunication in Human-Computer Interaction,2004,2915(2004):288-299.
[37] Shimada N, Kimura K, Shirai Y. Real-time3-D hand posture estimation based on2-Dappearance retrieval using monocular camera. ICCV Workshop on Recognition, Analysis, andTracking of Faces and Gestures in Real-Time Systems, Vancouver, Canada, July13-13,2001:23-30.
[38] Nolker C, Ritter H. Visual recognition of continuous hand postures. IEEE Transactions onNeural Networks,2002,13(4):983-994.
[39] Rosales R, Athitsos V, Sigal L, et al.3D hand pose reconstruction using specialized mappings.IEEE International Conference on Computer Vision, Vancouver, Canada, July7-14,2001:378-385.
[40] Gun H, Turk M.3D hand pose reconstruction with ISOSOM. Advances in Visual Computing,2005,3804(2005):630-635.
[41]刘棠丽,吴心筱,梁玮,等.基于非参数信念传播的可行C-空间关节人手跟踪方法.计算机辅助设计与图形学学报,2008,20(4):476-481.
[42] Takao N, Shi J, Baker S. Tele-graffiti: a camera-projector based remote sketching system withhand-based user interface and automatic session summarization. International Journal ofComputer Vision,2003,53(2):115-133.
[43] Zhang Z, Wu Y, Shan Y. Visual panel: virtual mouse, keyboard and3D controller with anordinary piece of paper. ACM Workshop on Perceptive User Interfaces, Orlando, USA,November15-16,2001:219-226.
[44]徐一华,李善青,贾云得.一种基于视觉的手指屏幕交互方法.电子学报,2007,35(11):2236-2240.
[45] Du H, Charbon E. A virtual keyboard system based on multi-level feature matching. Conferenceon Human System Interactions, Krakow, Poland, May25-27,2008:176-181.
[46]于瀛洁,李雨浪,郑华东.一种基于视觉的手指与全息影像交互研究.激光与红外,2010,40(4):447-452.
[47]郭康德,张明敏,孙超,等.基于视觉技术的三维指尖跟踪算法.计算机研究与发展,2010,47(6):1013-1019.
[48]祝世平,强锡富.用于摄像机定位的单目视觉方法研究.光学学报,2001,21（3）:339-343.
[49]游素亚,徐光佑.立体视觉研究的现状和进展.中国图像图形学报,1997,2(1):17-23.
[50]张辉,张丽艳,陈江,等.基于平面模板自由拍摄的双目立体测量系统的现场标定.航空学报,2007,28(3):695-701.
[51] Devernay F, Meteus D, Guilbert M. Multi-camera scene flow by tracking3D points and surfels.Computer Vision and Pattern Recognition Workshop, Washington DC, USA, June17-22,2006:2203-2212.
[52] Liu Bing, Yu Maoyuan, Maier Dennis, et al. An efficient and accurate method for3D-pointreconstruction from multiple views. International Journal of Computer Vision,2005,65(3):175-188.
[53] Wilburn B, Joshi N, Vaish V, et al. High performance imaging using large camera arrays. ACMTransactions on Graphics,2005,24(3):765-776.
[54] Wilburn B. High-performance imaging using arrays of inexpensive cameras. California:Stanford University,2005.
[55] Vaish V, Garg G, Talvala E V, et al. Synthetic aperture focusing using a shear-warp factorizationof the viewing transform. IEEE Computer Society Conference on Computer Vision and PatternRecognition, Los Alamitos: IEEE Computer Society Press,2005:129-136.
[56] Chai G B, Gu H B, Wu D S, et al. A research on hand position detection by camera array.Information Technology Journal,2012,11(1):110-117.
[57] Liu B, Yu M, Maier D, Manner R. An efficient and accurate method for3D-point reconstructionfrom multiple views. International Journal of Computer Vision,2005,65(3):175-188.
[58] Devernay F, Mateus D, Guilbert M. Multi-camera scene flow by tracking3-d points and surfels.IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006:2203-2212.
[59] Kakadiaris I, Metaxas D. Model based estimation of3D human motion with occlusion based onactive multi-viewpoint selection. IEEE Computer Society Conference on Computer Vision andPattern Recognition, San Francisco,1996:81-87.
[60] Gavrila D M, Davis L S.3D model-based tracking of humans in action: a multi-view approach.IEEE Computer Society Conference on Computer Vision and Pattern Recognition, SanFrancisco,1996:73-80.
[61] Hoshino K, Tomida M. Quick and accurate estimation of human3D hand posture. IntelligentService Robtics,2010,3(1):11-19.
[62]刘俊梅,阮秋琦.一种复杂背景下的手势分割新方法.北京电子科技学院学报,2006,14(2):23-27.
[63] Starner T, Weaver J, Pentland A. Real-time American sign language recognition using desk andwearable computer based video. IEEE transaction on Pattern Analysis and machine Intelligence,1998,20(12):1371-1375.
[64] Hyeon K L, Jin H K. An HMM-based threshold model approach for gesture recognition. IEEETransaction and PatternAnalysis and Machine Intelligence,1999,21(10):961-973.
[65]李清水,方志刚.手势识别技术及其在人机交互中的应用.人类工效学,2002,8(1):27-29.
[66] Kass M, Witkin A P, Terzopoulos D. Snakes: active contour models. International Journal ofComputer Vision,1988,1(4):321-331.
[67]杜威,李华.基于单目视觉的手势识别系统.工程图学学报,2000,21(3):133-138.
[68] He X，Yan S，Hu Y. Face recognition using laplacian faces.IEEE Trans.On Pattern Analysis andMachine Intelligence,2005,27(3):328-320.
[69] Habili N, Lim C C. Hand and face segmentation using motion and color cues in digital imagesequences. IEEE International Conference on Multimedia&Expo2001,2001:370-380.
[70] Gonzalez R C, Woods R E. Digital image processing.阮秋琦,阮宇智,等译.北京:电子工业出版社,2007.
[71] Hsu RL, Abdel M M, Jain A.K. Face detection in color images. Pattern Analysis and MachineIntelligence,2002,24(5):696-706.
[72]陈锻生,刘政凯.肤色检测技术综述.计算机学报,2006,29(2):194-207.
[73] Waggoner D F, Zha T. Normalization, probability distribution, and impulse responses. FederalReserve Bank of Atlanta Working Paper97-11,1997.
[74]牛庆肖,张桦,徐光平,等.基于链码和快速傅里叶变换的轮廓描绘方法.光电子·激光,2011,22(12):1857-1861.
[75] Wypij D. Spline and smoothing approaches to fitting flexible models for the analysis ofpulmonary function data. American Journal of Respiratory and Critical Care Medicine,1996,154:223-228.
[76] Kano H, Nakata H, Martin C F. Optimal curve fitting and smoothing using normalized uniformB-splines: a tool for studying complex systems. Applied Mathematics and Computation,2005,169(1):96-128.
[77] Yu D G, Yan H. An efficient algorithm for smoothing binary image contours. InternationalConference on Pattern Recognition, Aug.25-29,1996:403-407.
[78]李国辉,柳伟,曹莉华.一种基于颜色特征的图象检索方法.中国图象图形学报,1999,4(3):248-255.
[79]田玉敏,林高全.基于颜色特征的彩色图像检索方法.西安电子科技大学学报,2002,29(1):43-46.
[80]孙君顶,崔江涛,毋小省,等.基于颜色和形状特征的彩色图像检索方法.中国图象图形学报,2004,9(7):820-827.
[81]孙君顶,毋小省.基于分块主色和形状特征的彩色图像检索.光电工程,2006,33(12):85-90.
[82]万华林, Morshed U C,胡宏,等.图像纹理特征及其在CBIR中的应用.计算机辅助设计与图形学学报,2003,15(2):195-199.
[83]刘丽,匡纲要.图像纹理特征提取方法综述.中国图象图形学报,2009,14(4):622-635.
[84] Hu M K. Visual pattern recognition by moment invariants. IRE Transactions on InformationTheory,1962,8(2):179-187.
[85] Khotanzad A, Hong Y H. Invariant image recognition by Zernike moments. Pattern Analysis andMachine Intelligence,1990,12(5):489-497.
[86]孙丽萍,郭宝龙,李雷达.一种基于Krawtchouk矩的视频水印算法.光电子·激光,2008,19(5):671-675.
[87] Zhang D S. Image retrieval based on shape. Australia, Mareh, Monash University,2002.
[88] Lu G J, Sajjanhar A. Region-based shape representation and similarity measure suitable forcontent-based image retrieval. Multimedia Systems,1999,7(2):165-174.
[89] Chakrabarti K, Binderberger M O, Porkaew K, et al. Similar shape retrieval in MARS. IEEEInternational Conference on Multimedia and Expo, New York, USA, July30-August2,2000:709-712.
[90] Safar M, Shahabi C, Sun X. Image retrieval by shape: a comparative study. IEEE InternationalConference on Multimedia and Expo, New York, USA, July30-August2,2000:141-144.
[91] Goshtasby A. Description and discrimination of planar shapes using shape matrices. IEEETransactions on Pattern Analysis and Machine Intelligence,1985, PAMI-7(6):738-743.
[92] Loncaric S. Asurvey of shape analysis techniques. Pattern Recognition,1998,31(8):983-1001.
[93] Young I T, Walker J E, Bowie J E. An analysistechnique for biological shape. Information andControl,25(4):357-370.
[94] Peura M, Iivarinen J. Efficiency of simple shape descriptors.3rd International Workshop onVisual Form, Capri, Italy, May28-30,1997:443-451.
[95] Rui Y, She A C, Huang T S. Modified Fourier descriptor for shape representation. InternationalWorkshop on Image Databases and Multi-Media Search, Amsterdam,1996:47-58.
[96] Ohm J R, Bunjamin F, Liebsch W, et al. A set of visual feature descriptors and their combinationin a low-level description scheme. Signal Processing: Image Communication,2000,16:157-179.
[97] Chuang G C H and Kuo C C J. Wavelet descriptor of planar curves: theory and applications.IEEE Transactions on Image Processing,1996,5(1):56-70.
[98] Dalal N, Triggs B. Histograms of oriented gradients for human detection. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition, San Diego, USA, June25-25,2005:886-893.
[99] Papageorgiou C, Poggio T. A trainable system for object detection. International Journal ofComputer Vision,2000,38(1):15-33.
[100] Swain M J, Ballard D H. Color indexing. International Journal of Computer Vision,1991,7(1):11-32.
[101]卢汉清.图像视频信号的浏览与检索.中国图象图形学报(B),2000,5(1):5-9.
[102] Stricker M, Orengo M. Similarity of color images. Storage and Retrieval for Image and VideoDatabases III,1995,381(1995):381-392.
[103] Pass G, Zabih R. Histogram refinement for content-based image retrieval. IEEE Workshop onApplications of Computer Vision, Sarasota, USA, Dec.2-4,1996:96-102.
[104] Huang Jing. Color-spatial image indexing and applications. Cornell University, New York,1998.
[105] Han J, Kamber M. Data Mining: concepts and techniques:2nd edition. Morgan KaufmannPublications,2006.
[106] Swain M J. Interactive Indexing into Image Databases. Storage and Retrieval for Image andVideo Databases,1993,95(1993):95-103.
[107] Barla A, Odone F, Verri A. Histogram intersection kernel for image classification. InternationalConference on Image Processing, Sept14-17,2003:513-516.
[108] Smith J R. Integrated spatial and feature image systems: retrieval, analysis and compression.Columbia University, New York,1997.
[109] Amari S, Cichocki A, Yang H H. A new learning algorithm for blind signal separation. Neuraland Information Processing Systems,1996,8:757-763.
[110] Puzicha J, Rubner Y, Tomasi C, et al. Empirical evaluation of dissimilarity measures for colorand texture. International Conference on Computer Vision, Corfu, Greece, Sept.,1999:1165-1173.
[111]曲永宇,刘清,郭建明,等.基于HOG和颜色特征的行人检测.武汉理工大学学报,2011,33(4):134-138.
[112] Indyk P, Motwani R. Approximate Nearest Neighbors: Towards Removing the Curse ofDimensionality. Symposium on Theory of Computing,1998:604-613.
[113] Arya S, Mount D M, Netanyahu N S, et al. An optimal algorithm for approximate nearestneighbor searching in fixed dimensions. Journal of the ACM,1998,45(6):891-923.
[114] Bennett K P, Fayyad U, Geiger D. Density-based indexing for approximate nearest-neighborqueries. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,San Diego, USA,1999:233-243.
[115] Guttman A. R-trees: A dynamic index structure for spatial searching. SIGMOD'84Conference,Boston, USA, June,1984:47-57.
[116] Sellis T, Roussopoulos N, Faloutsos C. The R+-tree: A dynamic index for multidimensionalobjects. International Conference on Very Large Data Bases, Brighton, UK, Sept.,1987:507-518.
[117] Beckmann N, Kriegel H P, Schneider R, et al. The R*-tree: An efficient and robust accessmethod for points and rectangles. SIGMOD'90Conference, Atlantic City, USA, June,1990:322-331.
[118] Berchthold S, Keim D A, Kriegel H P. The X-tree: An index structure method forhigh-dimensional data. International Conference on Very Large Data Bases, Bombay, India,1996:28-39.
[119] White D A, Jain R. Similarity indexing with the SS-tree. International Conference on DataEngineering, New Orleans, LA, USA, Feb.26-Mar1,1996:516-523.
[120] Katayama N, Satoh S. The SR-tree, an index structure for high-dimensional nearest neighborqueries. SIGMOD'97Conference, Tucson, Arizona, USA, May13-15,1997:369-380.
[121] Bentley J L. Multidimensional binary search trees used for associative searching.Communications of the ACM,1975,18(9):509-517.
[122] Bentley J L, Friedman J H. Data structures for range searching. ACM Computing Surveys,1979,11(4):397-409.
[123] Robinson J T. The KDB-tree: a search structure for large multidimensional dynamic indexes.SIGMOD'81Conference, Ann Arbor, MI, USA, Apr.,1981:10-18.
[124] Finkel R, Bentley J. Quad trees: a data structure for retrieval of composite keys. ActaInformation,1974,4(1):1-9.
[125] Berchtold S, Keim D A. High-dimensional index structures: database support for next decade'sapplications. SIGMOD'98Conference, Seattle, WA, USA, June2-4,1998.
[126] Berchtold S, Bohm C, Kriegal H P. The pyramid-technique: towards breaking the curse ofdimensionality. SIGMOD'98Conference, Seattle, WA, USA, June2-4,1998.
[127] Weber R, Schek H J, Blott S. A quantitative analysis and performance study for similarity-searchmethods in high-dimensional spaces. International Conference on Very Large Data Bases, NewYork City, USA, August24-27,1998:194-205.
[128] Ferhatosmanoglu H, Tuncel E, Agrawal D. Vector approximation based indexing fornon-uniform high dimensional datasets. International Conference on Information andKnowledge Management, New York, ACM Press,2000:202~209.
[129] Cha G H, Zhu X, Petkovic P, et al. An efficient indexing method for nearest neighbor searches inhigh-dimensional image databases. IEEE Transactions on Multimedia,2002,4(1):76-87.
[130] Arya S, Mount D M, Netanyahu N S, et al. An optimal algorithm for approximate nearestneighbor searching in fixed dimensions. Journal of the ACM,1998,45(6):891-923.
[131] Gionis A, Indyk P, Motwani. Similarity search in high dimensions via hashing. InternationalConference on Very Large Data Bases, Edinburgh, Scotland, September7-10,1999:518-529.
[132] Datar M, Immorlica N, Indyk P, et al. Locality-sensitive hashing scheme based on p-stabledistributions. Annual Symposium on Computational Geometry, Brooklyn, New York, USA, June9-11,2004:253-262.
[133] Zolotarev V M. One-dimensional stable distributions. America Math Science Translion of MathMonographs,1986.
[134] Buhler J. Efficient large-scale sequence comparison by locality-sensitive. Bioinformatics,2001,17(5):419-428.
[135] Lv Q, Josephson W, Wang Z, et al. Multi-probe LSH: efficient indexing for high-dimensionalsimilarity search. International Conference on Very Large Data Bases, Vienna, Austria,September23-27,2007:950-961.
[136] Dong W, Wang Z, Josephson W, et al. Modeling LSH for performance tuning. ACM Conferenceon Information and Knowledge Management, Napa Valley, USA, October26-30,2008.
[137] Andoni A, Indyk P. Near-optimal hashing algorithms for approximate nearest neighbor in highdimensions. Annual IEEE Symposium on Foundations of Computer Science, Berkeley,California, USA, October21-24,2006:459-468.
[138] Joly A, Buisson O. A posteriori multi-probe locality sensitive hashing. ACM InternationalConference on Multimedia, Vancouver, BC, Canada, Oct.27-31,2008:209-218.
[139]冯志全,杨波,李毅,等.以时间优化为目标的粒子滤波手势跟踪方法研究.电子学报,2009,37(9):1989-1995.
[140] Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with physical forces.Computer Vison and Image Understanding,2001,81(3):328-357.
[141] Ueda E, Matsumoto Y, Imai M, et al. A hand-pose estimation for vision-based human interfaces.IEEE Transactions on Industrial Electronics,2003,50(4):676-684.
[142] Hamada Y, Shimada N, Shirai Y. Hand shape estimation using sequence of multiple viewpointimages based on transition network. Electronics and Communications in Japan,2004,87(8):33-42.
[143] Guan H, Chang J S, Chen L, et al. Multi-view appearance-based3D hand pose estimation.Computer Vision and Pattern Recognition Workshop, New York, USA, June17-22,2006:154-159.
[144] Ho MF, Tseng CY, Lien CC, et al. A multi-view vision-based hand motion capturing system.Pattern Recognition,2011,44(2):443-453.
[145] Romero J, Kjellstrom H, Kragic D. Hands in action: real-time3D reconstruction of hands ininteracton with objects. IEEE International Conference on Robotics and Automation,2010:458-463.
[146] Romero J, Kjellstrom H, Kragic D. Monocular real-time3D articulated hand pose estimation.IEEE-RAS International Conference on Humanoid Robots,2009:87-92.
[147]柴功博,顾宏斌,孙瑾.多颜色标记三维定位以及标记点稳定性研究.武汉理工大学学报,2011,33(5):681-684.
[148] Adams R, Bischof L. Seeded region growing. Pattern Analysis and Machine Intelligence,1994,16(6):641-647.
[149] Homma K, Takenaka E. An image processing method for feature extraction of space-occupyinglesions. Journal of Nuclear Medicine,1986,26(12):1472-1477.
[150] Joseph O’Rourke. Computational geometry. Cambridge, UK: CambridgeUniversity Press,1998.
[151] Yao A C. A lower bound to finding convex hulls. Journal of ACM,1981,28(4):780-787.
[152]吴文周,李利番,王结臣.平面点集凸包Graham算法的改进.测绘科学,2011,35(6):123-125.
[153]顾人舒,顾宏斌,汤勇.应用多个正交视角轮流逼近三维目标的坐标.中国图象图形学报,2011,16(11):1996-2001.
[154] Hawkings J, George D. Hierarchical temporal memory: concepts, theory, and terminology.Whitepaper, Numenta Inc,2006.
[155] George D, Hawkings J. Towards a mathematical theory of cortical micro-circuits. PLoSComputational Biology,2009,5(10): e1000532.
[156] Bobier B A, Wirth M. Content-based image retrieval using hierarchical temporal memory. ACMInternational Conference on Multimedia, New York: ACM Press,2008:925-928.
[157] Bundzel M, Hashimoto S. Object identification in dynamic images based on thememory-prediction theory of brain function. Journal of Intelligent Learning Systems andApplications,2010,2(4):212-220.
[158] Sassi F, Ascari L, Cagnoni S. Classifying human body acceleration patterns using a hierarchicaltemporal memory. Emergent Perspectives in Artificial Intelligence,2009:496-505.
[159] Gil-Garcia R J, Badia-Contelles J M, Pons-Porrata A. A general framework for agglomerativehierarchical clustering algorithms. International Conference on Pattern Recognition. LosAlamitos: IEEE Computer Society Press,2006:569-572.
[160] Nikam S B, Goel P, Tapadar R, et al. Combining gabor local texture pattern and wavelet globalfeatures for fingerprint matching. International Conference on Computational Intelligence andMultimedia Applications, Los Alamitos: IEEE Computer Society Press,2007:409-416.
[161] George D, Jaros B. The HTM learning algorithms. White Paper, Numenta Inc,2007.
[162] Freedman B, Shpunt A, Machline M, et al. Depth mapping using projected patterns. Prime SenseLtd, United States,2008.
[2] Sturman D J, Zeltzer D. A survey of glove-based input. IEEE Transaction on Computer Graphicsand Applications,1994,14(1):30-39.
[3]任程,戴树岭.基于数据手套的逼真虚拟手的实现.系统仿真学报,2008,20(22):6214-6217.
[4]宿春慧,杨方廷,涂颖.基于数据手套虚拟训练系统的研究与实现.系统仿真学报,2009,10(21):189-192.
[5] Livingston M A, State A. Magnetic tracker calibration for improved augmented realityregistration. Teleoperators and Virtual Environments,1997,6(5):532-546.
[6] Gu H B, Wu D S, Liu H. Development of a novel low-cost flight simulator for pilot training.World Academy of Science, Engineering and Technology,2009,60:685-689.
[7]罗斌,姚鹏,翁冬冬,等.基于混合现实的新型轻量级飞行模拟器系统.系统仿真学报,2009,21(17):5406-5410.
[8] Pavlovic V I, Sharma R, Huang T S. Visual interpretation of hand gestures for human-computerinteraction: a review. Pattern Analysis and Machine Intelligence,1997,19(7):677-695.
[9] Kuch J J. Vision-based hand modeling and gesture recognition for human computer interaction.Master’s Thesis, Univ. of Illinois at Urbana-Champaign,1994.
[10] Regh J M, Kanade T. DigitEyes: vision-based hand tracking for human-computer interaction.Motion of Non-Rigid and Articulated Objects,1994:16-22.
[11]梁路宏,艾海舟,徐光祐,等.人脸检测研究综述.计算机学报,2002,25(5):449-458.
[12] Rehg J, Kanade T. Visual tracking of self-occluding articulated objects. Technical ReportCMU-CS-94-224, Carnegie Mellon University,1994.
[13] Lathuiliere F, Herve J Y. Visual hand posture tracking in a gripper guiding application. IEEEInternational Conference Robotics and Automation, San Francisco, USA, April:24-28,2000:1688-1694.
[14] Lee J, Kunii T L. Model-based analysis of hand posture. Computer Graphics and Applications,1995,15(5):77-86.
[15] Sasaki A, Yolota S, Ohyama Y. Hand pose estimation from camera images of ring-shapedmarkers. ICCAS-SICE, Fukuoka, Japan, Aug.18-21,2009:3255-3259.
[16] Usabiaga J, Erol A, Bebis G, et al. Global hand pose estimation by multiple camera ellipsetracking. Advances in Visual Computing.2006,4291(2006):122-132.
[17] Zappi V, Brogni A, Caldwell D. Passive hand pose recognition in virtual reality. IEEESymposium on3D User Interfaces, Westin Waltham-Boston, USA, March20-212010:143-144.
[18] Koike H, Sato Y, Kobayashi Y. Integrating paper and digital information on EnhancedDesk: amethod for realtime finger tracking on an augmented desk system. ACM Transactions onComputer-Human Interaction,2001,8(4):307-322.
[19]杨端端,金连文,尹俊勋.手指书写汉字识别系统中的指尖检测方法.华南理工大学学报:自然科学版,2007,35(1):58-63.
[20] Segen J, Kumar S. Gesture VR: vision-based3d hand interace for spatial interaction. ACMInternational Conference on Multimedia, Bristol, UK, September12-16,1998:455-464.
[21] Wu A, Shah M, Da V. A virtual3D blackboard:3D finger tracking using a single camera.International Conference on Automatic Face and Gesture Recognition,2000:536-543.
[22] Caglar M B, Lobo N. Open hand detection in a cluttered single image using finger primitives.Computer Vision and Pattern Recognition Workshop, June17-22,2006:148-153.
[23]梅萍华,李斌,朱中的,等.基于径向对称变换的实时指尖检测算法.中国科学技术大学学报,2011,41(2):101-107.
[24] Rehg J, Kanade T. Visual tracking of high dof articulated structures: an application to humanhand tracking. Lecture Notes in Computer Science,1994,801(1994):35-46.
[25] Wu Y, Huang T S. Capturing articulated human hand motion: a divide-and-conquer approach.IEEE International Conference on Computer Vision, Kerkyra, Greece, September20-27,1999:606-611.
[26] Wu Y, Lin J Y, Huang T S. Capturing natural hand articulation. IEEE International Conferenceon Computer Vision, Vancouver, Canada, July7-14,2001:426-432.
[27] Lin J Y, Wu Y, Huang T S. Capturing human hand motion in image sequences. Workshop onMotion and Video Computing, Dec5-6,2002:99-104.
[28] Heap T, Hogg D. Towards3D hand tracking using a deformable model. International Conferenceon Automatic Face and Gesture Recognition, Killington, USA, Oct.14-16,1996:140-145.
[29] Zhou H, Huang T S. Tracking articulated hand motion with eigen dynamics analysisl. IEEEInternational Conference on Computer Vision, Nice, France, Oct.13-16,2003:1102-1109.
[30] Bray M, Koller-Meier E, Muller P, et al.3D hand tracking by rapid stochastic gradient descentusing a skinning model. European Conference on Visual Media Production, March15-16,2004:59-68.
[31] Bray M, Koller-Meier E, Gool L V. Smart particle filtering for high-dimensional tracking.Computer Vision and Image Understanding,2007,106(1):116-129.
[32] Lien C C. A scalable model-based hand posture analysis system. Machine Vision andApplications,2005,16(3):157-169.
[33] Rehg J M, Kanade T. Model-based tracking of self-occluding articulated objects. InternationalConference on Computer Vision, Cambridge, MA, USA, Jun.20-23,1995:612-617.
[34] Athitsos V, Sclaroff S.3D hand pose estimation by finding appearance-based matches in a largedatabase of training views. IEEE Workshop on Cues in Communication, Kauai, Hawaii, USA,December9,2001.
[35] Athitsos V, Sclaroff S. An appearance-based framework for3D hand shape classification andcamera viewpoint estimation. IEEE International Conference on Automatic Face and GestureRecognition, Washington, USA, May20-21,2002:40-45.
[36] Athitsos V, Sclaroff S. Database indexing methods for3D hand pose estimation. Gesture-BasedCommunication in Human-Computer Interaction,2004,2915(2004):288-299.
[37] Shimada N, Kimura K, Shirai Y. Real-time3-D hand posture estimation based on2-Dappearance retrieval using monocular camera. ICCV Workshop on Recognition, Analysis, andTracking of Faces and Gestures in Real-Time Systems, Vancouver, Canada, July13-13,2001:23-30.
[38] Nolker C, Ritter H. Visual recognition of continuous hand postures. IEEE Transactions onNeural Networks,2002,13(4):983-994.
[39] Rosales R, Athitsos V, Sigal L, et al.3D hand pose reconstruction using specialized mappings.IEEE International Conference on Computer Vision, Vancouver, Canada, July7-14,2001:378-385.
[40] Gun H, Turk M.3D hand pose reconstruction with ISOSOM. Advances in Visual Computing,2005,3804(2005):630-635.
[41]刘棠丽,吴心筱,梁玮,等.基于非参数信念传播的可行C-空间关节人手跟踪方法.计算机辅助设计与图形学学报,2008,20(4):476-481.
[42] Takao N, Shi J, Baker S. Tele-graffiti: a camera-projector based remote sketching system withhand-based user interface and automatic session summarization. International Journal ofComputer Vision,2003,53(2):115-133.
[43] Zhang Z, Wu Y, Shan Y. Visual panel: virtual mouse, keyboard and3D controller with anordinary piece of paper. ACM Workshop on Perceptive User Interfaces, Orlando, USA,November15-16,2001:219-226.
[44]徐一华,李善青,贾云得.一种基于视觉的手指屏幕交互方法.电子学报,2007,35(11):2236-2240.
[45] Du H, Charbon E. A virtual keyboard system based on multi-level feature matching. Conferenceon Human System Interactions, Krakow, Poland, May25-27,2008:176-181.
[46]于瀛洁,李雨浪,郑华东.一种基于视觉的手指与全息影像交互研究.激光与红外,2010,40(4):447-452.
[47]郭康德,张明敏,孙超,等.基于视觉技术的三维指尖跟踪算法.计算机研究与发展,2010,47(6):1013-1019.
[48]祝世平,强锡富.用于摄像机定位的单目视觉方法研究.光学学报,2001,21（3）:339-343.
[49]游素亚,徐光佑.立体视觉研究的现状和进展.中国图像图形学报,1997,2(1):17-23.
[50]张辉,张丽艳,陈江,等.基于平面模板自由拍摄的双目立体测量系统的现场标定.航空学报,2007,28(3):695-701.
[51] Devernay F, Meteus D, Guilbert M. Multi-camera scene flow by tracking3D points and surfels.Computer Vision and Pattern Recognition Workshop, Washington DC, USA, June17-22,2006:2203-2212.
[52] Liu Bing, Yu Maoyuan, Maier Dennis, et al. An efficient and accurate method for3D-pointreconstruction from multiple views. International Journal of Computer Vision,2005,65(3):175-188.
[53] Wilburn B, Joshi N, Vaish V, et al. High performance imaging using large camera arrays. ACMTransactions on Graphics,2005,24(3):765-776.
[54] Wilburn B. High-performance imaging using arrays of inexpensive cameras. California:Stanford University,2005.
[55] Vaish V, Garg G, Talvala E V, et al. Synthetic aperture focusing using a shear-warp factorizationof the viewing transform. IEEE Computer Society Conference on Computer Vision and PatternRecognition, Los Alamitos: IEEE Computer Society Press,2005:129-136.
[56] Chai G B, Gu H B, Wu D S, et al. A research on hand position detection by camera array.Information Technology Journal,2012,11(1):110-117.
[57] Liu B, Yu M, Maier D, Manner R. An efficient and accurate method for3D-point reconstructionfrom multiple views. International Journal of Computer Vision,2005,65(3):175-188.
[58] Devernay F, Mateus D, Guilbert M. Multi-camera scene flow by tracking3-d points and surfels.IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006:2203-2212.
[59] Kakadiaris I, Metaxas D. Model based estimation of3D human motion with occlusion based onactive multi-viewpoint selection. IEEE Computer Society Conference on Computer Vision andPattern Recognition, San Francisco,1996:81-87.
[60] Gavrila D M, Davis L S.3D model-based tracking of humans in action: a multi-view approach.IEEE Computer Society Conference on Computer Vision and Pattern Recognition, SanFrancisco,1996:73-80.
[61] Hoshino K, Tomida M. Quick and accurate estimation of human3D hand posture. IntelligentService Robtics,2010,3(1):11-19.
[62]刘俊梅,阮秋琦.一种复杂背景下的手势分割新方法.北京电子科技学院学报,2006,14(2):23-27.
[63] Starner T, Weaver J, Pentland A. Real-time American sign language recognition using desk andwearable computer based video. IEEE transaction on Pattern Analysis and machine Intelligence,1998,20(12):1371-1375.
[64] Hyeon K L, Jin H K. An HMM-based threshold model approach for gesture recognition. IEEETransaction and PatternAnalysis and Machine Intelligence,1999,21(10):961-973.
[65]李清水,方志刚.手势识别技术及其在人机交互中的应用.人类工效学,2002,8(1):27-29.
[66] Kass M, Witkin A P, Terzopoulos D. Snakes: active contour models. International Journal ofComputer Vision,1988,1(4):321-331.
[67]杜威,李华.基于单目视觉的手势识别系统.工程图学学报,2000,21(3):133-138.
[68] He X，Yan S，Hu Y. Face recognition using laplacian faces.IEEE Trans.On Pattern Analysis andMachine Intelligence,2005,27(3):328-320.
[69] Habili N, Lim C C. Hand and face segmentation using motion and color cues in digital imagesequences. IEEE International Conference on Multimedia&Expo2001,2001:370-380.
[70] Gonzalez R C, Woods R E. Digital image processing.阮秋琦,阮宇智,等译.北京:电子工业出版社,2007.
[71] Hsu RL, Abdel M M, Jain A.K. Face detection in color images. Pattern Analysis and MachineIntelligence,2002,24(5):696-706.
[72]陈锻生,刘政凯.肤色检测技术综述.计算机学报,2006,29(2):194-207.
[73] Waggoner D F, Zha T. Normalization, probability distribution, and impulse responses. FederalReserve Bank of Atlanta Working Paper97-11,1997.
[74]牛庆肖,张桦,徐光平,等.基于链码和快速傅里叶变换的轮廓描绘方法.光电子·激光,2011,22(12):1857-1861.
[75] Wypij D. Spline and smoothing approaches to fitting flexible models for the analysis ofpulmonary function data. American Journal of Respiratory and Critical Care Medicine,1996,154:223-228.
[76] Kano H, Nakata H, Martin C F. Optimal curve fitting and smoothing using normalized uniformB-splines: a tool for studying complex systems. Applied Mathematics and Computation,2005,169(1):96-128.
[77] Yu D G, Yan H. An efficient algorithm for smoothing binary image contours. InternationalConference on Pattern Recognition, Aug.25-29,1996:403-407.
[78]李国辉,柳伟,曹莉华.一种基于颜色特征的图象检索方法.中国图象图形学报,1999,4(3):248-255.
[79]田玉敏,林高全.基于颜色特征的彩色图像检索方法.西安电子科技大学学报,2002,29(1):43-46.
[80]孙君顶,崔江涛,毋小省,等.基于颜色和形状特征的彩色图像检索方法.中国图象图形学报,2004,9(7):820-827.
[81]孙君顶,毋小省.基于分块主色和形状特征的彩色图像检索.光电工程,2006,33(12):85-90.
[82]万华林, Morshed U C,胡宏,等.图像纹理特征及其在CBIR中的应用.计算机辅助设计与图形学学报,2003,15(2):195-199.
[83]刘丽,匡纲要.图像纹理特征提取方法综述.中国图象图形学报,2009,14(4):622-635.
[84] Hu M K. Visual pattern recognition by moment invariants. IRE Transactions on InformationTheory,1962,8(2):179-187.
[85] Khotanzad A, Hong Y H. Invariant image recognition by Zernike moments. Pattern Analysis andMachine Intelligence,1990,12(5):489-497.
[86]孙丽萍,郭宝龙,李雷达.一种基于Krawtchouk矩的视频水印算法.光电子·激光,2008,19(5):671-675.
[87] Zhang D S. Image retrieval based on shape. Australia, Mareh, Monash University,2002.
[88] Lu G J, Sajjanhar A. Region-based shape representation and similarity measure suitable forcontent-based image retrieval. Multimedia Systems,1999,7(2):165-174.
[89] Chakrabarti K, Binderberger M O, Porkaew K, et al. Similar shape retrieval in MARS. IEEEInternational Conference on Multimedia and Expo, New York, USA, July30-August2,2000:709-712.
[90] Safar M, Shahabi C, Sun X. Image retrieval by shape: a comparative study. IEEE InternationalConference on Multimedia and Expo, New York, USA, July30-August2,2000:141-144.
[91] Goshtasby A. Description and discrimination of planar shapes using shape matrices. IEEETransactions on Pattern Analysis and Machine Intelligence,1985, PAMI-7(6):738-743.
[92] Loncaric S. Asurvey of shape analysis techniques. Pattern Recognition,1998,31(8):983-1001.
[93] Young I T, Walker J E, Bowie J E. An analysistechnique for biological shape. Information andControl,25(4):357-370.
[94] Peura M, Iivarinen J. Efficiency of simple shape descriptors.3rd International Workshop onVisual Form, Capri, Italy, May28-30,1997:443-451.
[95] Rui Y, She A C, Huang T S. Modified Fourier descriptor for shape representation. InternationalWorkshop on Image Databases and Multi-Media Search, Amsterdam,1996:47-58.
[96] Ohm J R, Bunjamin F, Liebsch W, et al. A set of visual feature descriptors and their combinationin a low-level description scheme. Signal Processing: Image Communication,2000,16:157-179.
[97] Chuang G C H and Kuo C C J. Wavelet descriptor of planar curves: theory and applications.IEEE Transactions on Image Processing,1996,5(1):56-70.
[98] Dalal N, Triggs B. Histograms of oriented gradients for human detection. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition, San Diego, USA, June25-25,2005:886-893.
[99] Papageorgiou C, Poggio T. A trainable system for object detection. International Journal ofComputer Vision,2000,38(1):15-33.
[100] Swain M J, Ballard D H. Color indexing. International Journal of Computer Vision,1991,7(1):11-32.
[101]卢汉清.图像视频信号的浏览与检索.中国图象图形学报(B),2000,5(1):5-9.
[102] Stricker M, Orengo M. Similarity of color images. Storage and Retrieval for Image and VideoDatabases III,1995,381(1995):381-392.
[103] Pass G, Zabih R. Histogram refinement for content-based image retrieval. IEEE Workshop onApplications of Computer Vision, Sarasota, USA, Dec.2-4,1996:96-102.
[104] Huang Jing. Color-spatial image indexing and applications. Cornell University, New York,1998.
[105] Han J, Kamber M. Data Mining: concepts and techniques:2nd edition. Morgan KaufmannPublications,2006.
[106] Swain M J. Interactive Indexing into Image Databases. Storage and Retrieval for Image andVideo Databases,1993,95(1993):95-103.
[107] Barla A, Odone F, Verri A. Histogram intersection kernel for image classification. InternationalConference on Image Processing, Sept14-17,2003:513-516.
[108] Smith J R. Integrated spatial and feature image systems: retrieval, analysis and compression.Columbia University, New York,1997.
[109] Amari S, Cichocki A, Yang H H. A new learning algorithm for blind signal separation. Neuraland Information Processing Systems,1996,8:757-763.
[110] Puzicha J, Rubner Y, Tomasi C, et al. Empirical evaluation of dissimilarity measures for colorand texture. International Conference on Computer Vision, Corfu, Greece, Sept.,1999:1165-1173.
[111]曲永宇,刘清,郭建明,等.基于HOG和颜色特征的行人检测.武汉理工大学学报,2011,33(4):134-138.
[112] Indyk P, Motwani R. Approximate Nearest Neighbors: Towards Removing the Curse ofDimensionality. Symposium on Theory of Computing,1998:604-613.
[113] Arya S, Mount D M, Netanyahu N S, et al. An optimal algorithm for approximate nearestneighbor searching in fixed dimensions. Journal of the ACM,1998,45(6):891-923.
[114] Bennett K P, Fayyad U, Geiger D. Density-based indexing for approximate nearest-neighborqueries. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,San Diego, USA,1999:233-243.
[115] Guttman A. R-trees: A dynamic index structure for spatial searching. SIGMOD'84Conference,Boston, USA, June,1984:47-57.
[116] Sellis T, Roussopoulos N, Faloutsos C. The R+-tree: A dynamic index for multidimensionalobjects. International Conference on Very Large Data Bases, Brighton, UK, Sept.,1987:507-518.
[117] Beckmann N, Kriegel H P, Schneider R, et al. The R*-tree: An efficient and robust accessmethod for points and rectangles. SIGMOD'90Conference, Atlantic City, USA, June,1990:322-331.
[118] Berchthold S, Keim D A, Kriegel H P. The X-tree: An index structure method forhigh-dimensional data. International Conference on Very Large Data Bases, Bombay, India,1996:28-39.
[119] White D A, Jain R. Similarity indexing with the SS-tree. International Conference on DataEngineering, New Orleans, LA, USA, Feb.26-Mar1,1996:516-523.
[120] Katayama N, Satoh S. The SR-tree, an index structure for high-dimensional nearest neighborqueries. SIGMOD'97Conference, Tucson, Arizona, USA, May13-15,1997:369-380.
[121] Bentley J L. Multidimensional binary search trees used for associative searching.Communications of the ACM,1975,18(9):509-517.
[122] Bentley J L, Friedman J H. Data structures for range searching. ACM Computing Surveys,1979,11(4):397-409.
[123] Robinson J T. The KDB-tree: a search structure for large multidimensional dynamic indexes.SIGMOD'81Conference, Ann Arbor, MI, USA, Apr.,1981:10-18.
[124] Finkel R, Bentley J. Quad trees: a data structure for retrieval of composite keys. ActaInformation,1974,4(1):1-9.
[125] Berchtold S, Keim D A. High-dimensional index structures: database support for next decade'sapplications. SIGMOD'98Conference, Seattle, WA, USA, June2-4,1998.
[126] Berchtold S, Bohm C, Kriegal H P. The pyramid-technique: towards breaking the curse ofdimensionality. SIGMOD'98Conference, Seattle, WA, USA, June2-4,1998.
[127] Weber R, Schek H J, Blott S. A quantitative analysis and performance study for similarity-searchmethods in high-dimensional spaces. International Conference on Very Large Data Bases, NewYork City, USA, August24-27,1998:194-205.
[128] Ferhatosmanoglu H, Tuncel E, Agrawal D. Vector approximation based indexing fornon-uniform high dimensional datasets. International Conference on Information andKnowledge Management, New York, ACM Press,2000:202~209.
[129] Cha G H, Zhu X, Petkovic P, et al. An efficient indexing method for nearest neighbor searches inhigh-dimensional image databases. IEEE Transactions on Multimedia,2002,4(1):76-87.
[130] Arya S, Mount D M, Netanyahu N S, et al. An optimal algorithm for approximate nearestneighbor searching in fixed dimensions. Journal of the ACM,1998,45(6):891-923.
[131] Gionis A, Indyk P, Motwani. Similarity search in high dimensions via hashing. InternationalConference on Very Large Data Bases, Edinburgh, Scotland, September7-10,1999:518-529.
[132] Datar M, Immorlica N, Indyk P, et al. Locality-sensitive hashing scheme based on p-stabledistributions. Annual Symposium on Computational Geometry, Brooklyn, New York, USA, June9-11,2004:253-262.
[133] Zolotarev V M. One-dimensional stable distributions. America Math Science Translion of MathMonographs,1986.
[134] Buhler J. Efficient large-scale sequence comparison by locality-sensitive. Bioinformatics,2001,17(5):419-428.
[135] Lv Q, Josephson W, Wang Z, et al. Multi-probe LSH: efficient indexing for high-dimensionalsimilarity search. International Conference on Very Large Data Bases, Vienna, Austria,September23-27,2007:950-961.
[136] Dong W, Wang Z, Josephson W, et al. Modeling LSH for performance tuning. ACM Conferenceon Information and Knowledge Management, Napa Valley, USA, October26-30,2008.
[137] Andoni A, Indyk P. Near-optimal hashing algorithms for approximate nearest neighbor in highdimensions. Annual IEEE Symposium on Foundations of Computer Science, Berkeley,California, USA, October21-24,2006:459-468.
[138] Joly A, Buisson O. A posteriori multi-probe locality sensitive hashing. ACM InternationalConference on Multimedia, Vancouver, BC, Canada, Oct.27-31,2008:209-218.
[139]冯志全,杨波,李毅,等.以时间优化为目标的粒子滤波手势跟踪方法研究.电子学报,2009,37(9):1989-1995.
[140] Delamarre Q, Faugeras O.3D articulated models and multi-view tracking with physical forces.Computer Vison and Image Understanding,2001,81(3):328-357.
[141] Ueda E, Matsumoto Y, Imai M, et al. A hand-pose estimation for vision-based human interfaces.IEEE Transactions on Industrial Electronics,2003,50(4):676-684.
[142] Hamada Y, Shimada N, Shirai Y. Hand shape estimation using sequence of multiple viewpointimages based on transition network. Electronics and Communications in Japan,2004,87(8):33-42.
[143] Guan H, Chang J S, Chen L, et al. Multi-view appearance-based3D hand pose estimation.Computer Vision and Pattern Recognition Workshop, New York, USA, June17-22,2006:154-159.
[144] Ho MF, Tseng CY, Lien CC, et al. A multi-view vision-based hand motion capturing system.Pattern Recognition,2011,44(2):443-453.
[145] Romero J, Kjellstrom H, Kragic D. Hands in action: real-time3D reconstruction of hands ininteracton with objects. IEEE International Conference on Robotics and Automation,2010:458-463.
[146] Romero J, Kjellstrom H, Kragic D. Monocular real-time3D articulated hand pose estimation.IEEE-RAS International Conference on Humanoid Robots,2009:87-92.
[147]柴功博,顾宏斌,孙瑾.多颜色标记三维定位以及标记点稳定性研究.武汉理工大学学报,2011,33(5):681-684.
[148] Adams R, Bischof L. Seeded region growing. Pattern Analysis and Machine Intelligence,1994,16(6):641-647.
[149] Homma K, Takenaka E. An image processing method for feature extraction of space-occupyinglesions. Journal of Nuclear Medicine,1986,26(12):1472-1477.
[150] Joseph O’Rourke. Computational geometry. Cambridge, UK: CambridgeUniversity Press,1998.
[151] Yao A C. A lower bound to finding convex hulls. Journal of ACM,1981,28(4):780-787.
[152]吴文周,李利番,王结臣.平面点集凸包Graham算法的改进.测绘科学,2011,35(6):123-125.
[153]顾人舒,顾宏斌,汤勇.应用多个正交视角轮流逼近三维目标的坐标.中国图象图形学报,2011,16(11):1996-2001.
[154] Hawkings J, George D. Hierarchical temporal memory: concepts, theory, and terminology.Whitepaper, Numenta Inc,2006.
[155] George D, Hawkings J. Towards a mathematical theory of cortical micro-circuits. PLoSComputational Biology,2009,5(10): e1000532.
[156] Bobier B A, Wirth M. Content-based image retrieval using hierarchical temporal memory. ACMInternational Conference on Multimedia, New York: ACM Press,2008:925-928.
[157] Bundzel M, Hashimoto S. Object identification in dynamic images based on thememory-prediction theory of brain function. Journal of Intelligent Learning Systems andApplications,2010,2(4):212-220.
[158] Sassi F, Ascari L, Cagnoni S. Classifying human body acceleration patterns using a hierarchicaltemporal memory. Emergent Perspectives in Artificial Intelligence,2009:496-505.
[159] Gil-Garcia R J, Badia-Contelles J M, Pons-Porrata A. A general framework for agglomerativehierarchical clustering algorithms. International Conference on Pattern Recognition. LosAlamitos: IEEE Computer Society Press,2006:569-572.
[160] Nikam S B, Goel P, Tapadar R, et al. Combining gabor local texture pattern and wavelet globalfeatures for fingerprint matching. International Conference on Computational Intelligence andMultimedia Applications, Los Alamitos: IEEE Computer Society Press,2007:409-416.
[161] George D, Jaros B. The HTM learning algorithms. White Paper, Numenta Inc,2007.
[162] Freedman B, Shpunt A, Machline M, et al. Depth mapping using projected patterns. Prime SenseLtd, United States,2008.