期刊文献+

基于RGB-D摄像头的实时手指跟踪与手势识别 被引量:10

Real-time Fingertip Tracking and Gesture Recognition Using RGB-D Camera
下载PDF
导出
摘要 近些年,基于视觉的手部跟踪与手势识别一直是人机交互和计算机视觉等领域的研究热点。传统方法主要是使用单目或多目RGB摄像头等设备获得手部位置、方向等信息,但RGB摄像头易受到复杂背景、光照变化、纹理的限制,导致其准确性、实时性和鲁棒性都较差。随着可获得场景深度信息的家用RGB-Depth(RGB-D)摄像头的发展和上市,可以利用深度信息较好地克服上述环境问题。首先定义了一个基于RGB-D摄像头的3D交互空间,根据深度信息将手部区域从复杂背景、多变的光照条件下进行分割;然后提出了一种基于深度摄像头的手指识别和跟踪方法,该方法基于手部轮廓对人手及手指进行识别和跟踪;最后通过对手指位置和轨迹的跟踪进行手势识别,从而实现人机交互。对提出的方法进行的实验验证了它的准确性、实时性和鲁棒性。 In recent decades, visual interpretation of finger and hand gestures has been an attractive direction in both computer vision and human-computer interaction areas. Traditional methods use a monocular RGB camera or multiple RGB cameras to get hand information. But it is limited by clustered backgrounds,lighting conditions, textures and other environment factors, which makes the accuracy, robustness and efficiency cannot satisfy real-time interactions. With the coming of consumer-level RGB-D camera, above limitations can be overcame with depth data got from a RGB-D camera. We first defineed a 3D interaction space with the RGB-D camera and segmented the hand region from backgrounds with the help of depth information. Then we proposed a real-time finger recognition and tracking approach using a depth camera which mainly use the contour of hands. At last, the human-computer interaction was achieved with the position and trajectory of fingers from the above method. Based on the proposed method, we designed several experiments. The results validate the accuracy,effectiveness and robustness of our approach.
出处 《计算机科学》 CSCD 北大核心 2014年第10期50-52,61,共4页 Computer Science
基金 国家自然科学基金创新研究群体项目(61121001) 高等学校博士学科点专项科研基金(20120005130002) 国家杰出青年科学基金项目:网络环境中多媒体计算(60925010)资助
关键词 手指跟踪 手势识别 计算机视觉 人机交互 RGB-D摄像头 Finger tracking,Gesture recognition,Human-computer interaction,Computer vision,RGB-D camera
  • 相关文献

参考文献16

  • 1Vladimir I P,Rajeev S,Thomas S H.Visual Interpretation ofHand Gestures for Human-Computer Interaction:A Review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,9(7).
  • 2Ali E,George B,Mircea N,et al.Vision-based hand pose estimation:A review[J].Computer Vision and Image Understanding,2007(108):52-73.
  • 3Sushmita M,Tinku A.Gesture Recognition:A Survey[J].IEEE Transactions on Systems,MAN,and Cybernetics—Part C:A pplications and Reviews,2007,37(3).
  • 4Juan P W,Mathias K,Helman S,et al.Vision-Based Hand-Gesture Applications[J].Communications of the ACM,2011, 54(2).
  • 5Lars B,Ivan L,Tony L.Hand Gesture Recognition using Multi-Scale Colour Features,Hierarchical Models and Particle Filtering,Automatic Face and Gesture Recognition[C]∥Procee-dings.Fifth IEEE International Conference.May 2002:423-428.
  • 6Yikai F,Kongqiao W,Jian C,et al.A Real-time H andgestureRecognition Method[C]∥2007 IEEE International Conference on Multimedia and Expo.2007:995-998.
  • 7Kenji O,Yoichi S,Hideki K.Real-Time Fingertip Tracking and Gesture Recognition[J].IEEE Computer Graphics and Applications,2002,22(6):64-71.
  • 8Robert Y W,Jovan P.Real-Time Hand-Tracking with a Color Glove[J].ACM Transactions on Graphics (TOG), 2009,28(3).
  • 9Jesus S,Robin R M.Hand Gesture Recognition with Depth Images:A Review[C]∥RO-MAN,2012 IEEE.2012:411-417.
  • 10Iason O,Nikolaos K,Antonis A A.Efficient Model-based 3DTracking of Hand Articulations using Kinect[C]∥Proceeding of BMVC.2011.

二级参考文献65

  • 1李自勤,李琦,王骐.由统计特性分析激光主动成像系统图像的噪声性质[J].中国激光,2004,31(9):1081-1085. 被引量:27
  • 2von Hardenberg C, Berard F. Bare hand human-computer interaction [C] //Proceedings of ACM Workshop on Perceptive User Interface, Orlando, 2001:1-8.
  • 3Malik S, Ranian A, Balakrishnan R. Interacting with large displays from a distance with vision-tracked multi-finger gestural input [C] //Proceedings of the 18th Annual ACM Symposium on User Interface Software and Technology, Seattle, 2005:43-52.
  • 4Cao X, Balakrishnan R. VisionWand: interaction techniques for large displays using a passive wand tracked in 3D [C] // Proceedings of the 16th Annual ACM Symposium on User Interface Software and Technology, Vancouver, 2003 : 173 - 182.
  • 5Vlasic D, Adelsberger R, Vannucci G, et al. Practical motion capture in everyday surroundings [J]. ACM Transactions on Graphics, 2007, 26(3) : Article 35.1-35.9.
  • 6Liang X B, Zhang S, Li Q L, etal. Intuitive motion retrieval with motion sensors [C] //Proceedings of Computer Graphics International, Istanbul, 2008:64-71.
  • 7Shiratori T, Hodgins J K. Accelerometer-based user interfaces for the control of a physically simulated character [J]. ACM Transactions on Graphics, 2008, 27(5): Article 123.1-123.9.
  • 8Liang X B, Li Q L, Zhang X, et al. Performance driven motion choreographing with accelerometers [J]. Computer Animation and Virtual Worlds, 2009, 20:89-99.
  • 9Wilson A, Sharer S. XWand: UI for intelligent spaces [C] // Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Lauderdale, 2003:545-552.
  • 10Kallio S, Kela J, Korpipaa P, et al. User independent gesture interaction for small handheld devices [J]. International Journal of Pattern Recognition and Artificial Intelligence, 2006, 20(4): 505-524.

共引文献64

同被引文献66

  • 1路凯,李小坚,周金祥.基于肤色和边缘轮廓检测的手势识别[J].北方工业大学学报,2006,18(3):12-15. 被引量:10
  • 2S IL A N O N K , S U V O N V O R N N . H and m otion analysis fo rT h ai alphabet re cognitio n using H M M [J] . In te rn a tio n a lJournal o f In fo rm a tio n and E lectro nics E n g in e e rin g , 2 0 1 1 ,1 ( 1 ) : 6 5 -71.
  • 3JU A N P W , M A T H IA S K , H E L M A N S , et. al. V is io n -based hand-gesture ap plication s [J] . C om m unications ofthe A C M , 2 0 1 1 , 5 4 ( 2 ) : 6 0 -71.
  • 4H O L T E M B , M O E S LU N D T B , F IH L P. V ie w -in v a ria n tgesture re cognitio n using 3D op tica l flo w and harm onic m otion context [J] . C om puter V is io n and Image U nderstanding , 2 0 1 0 , 1 1 4 (1 2 ) : 1353-1361.
  • 5V IC E N T E A P , F A IS A L A A . C a lib ra tio n o f kin e m a ticbody sensor netw orks : K inect-based gauging o f data gloves" i n the w ild " [C] / / B o d y Sensor N etw orks ( B S N ) , 20131E E E In te rn a tio n a l Conference on. U S A , M A , Cam bridge :IE E E , 2 0 1 3 : 1-6.
  • 6R O B E R T Y W , JO V A N P. R eal-tim e h a n d -tra ckin g w ith acolor g lo ve [J] . A C M Transactions on G raphics ( T O G ) ,2 0 0 9 , 2 8 ( 3 ) :34 1-35 2.
  • 7Y A N G C , JA N G Y , B E H J , et a l. Gesture re cognitio n u singdepth-based hand tra ckin g fo r contactless c o n tro lle r applic a tio n [C] / / Consum er E lectro nics ( IC C E ) , 2012 IE E EIn te rn a tio n a l Conference on. Las V egas, N V : IE E E ,2 0 1 2 : 29 7-29 8.
  • 8王西颖,戴国忠,张习文,张凤军.基于HMM-FNN模型的复杂动态手势识别[J].软件学报,2008,19(9):2302-2312. 被引量:39
  • 9徐迟,李世其,王峻峰,彭涛.面向增强现实装配的虚实遮挡技术研究[J].机械设计与制造,2009(12):256-258. 被引量:6
  • 10梁秀波,张顺,李启雷,张翔,耿卫东.运动传感驱动的3D直观手势交互[J].计算机辅助设计与图形学学报,2010,22(3):521-526. 被引量:18

引证文献10

二级引证文献71

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部