首页 | 官方网站   微博 | 高级检索  
     

复杂背景下的手势分割与识别
引用本文:任海兵,祝远新,徐光祐,张晓平,林学誾.复杂背景下的手势分割与识别[J].自动化学报,2002,28(2):256-261.
作者姓名:任海兵  祝远新  徐光祐  张晓平  林学誾
作者单位:1.清华大学计算机科学与技术系媒体所,北京
基金项目:国家自然科学基金 (69873 0 2 2 ),国家“八六三”(863 -3 0 6-ZT0 3 -0 1 -1 )资助
摘    要:目前在基于单目视觉的手势识别中,手势分割技术几乎都是基于简单的背景或者要求 手势者带有特殊颜色的手套,给人机交互增加了一定的限制.本文融合人手颜色信息和手势运 动信息,两次利用种子算法对复杂背景下的手势进行分割.根据分割出的手区域大大加速了运动 特征参数的提取,并结合手区域的形状特征,建立手势的时空表观模型.识别时,采用独立分布的 多状态高斯概率模型,进行时间规整.手势训练集和测试集的识别率分别为97.8%和95.6%.

关 键 词:复杂背景    手势分割    手势识别    独立分布    多状态高斯概率模型
收稿时间:1999-10-20
修稿时间:1999年10月20

HAND GESTURE SEGMENTATION AND RECOGNITION WITH COMPLEX BACKGROUNDS
REN Hai-Bing,ZHU Yuan-Xin,XU Guang-You,ZHANG Xiao-Ping,LIN Xue-Yin.HAND GESTURE SEGMENTATION AND RECOGNITION WITH COMPLEX BACKGROUNDS[J].Acta Automatica Sinica,2002,28(2):256-261.
Authors:REN Hai-Bing  ZHU Yuan-Xin  XU Guang-You  ZHANG Xiao-Ping  LIN Xue-Yin
Affiliation:1.Media Institute,Department of Computer Science and Technology,Tsinghua University,Beijing
Abstract:Currently, in the vision based hand gesture recognition, almost all the technologies on hand gesture segmentation are based on simple backgrounds or on gloves in special colors, which give the human computer interaction some limitation. This paper presents a new method, which segments hand gestures with complex backgrounds by fusing skin chrominance and coarse image motion, and by using the seed algorithm twice. With the segmented hand areas, the algorithm for motion appearance parameters is accelerated greatly. By integrating temporal information, motion and shape appearances, a spatio temporal appearance model is proposed for representing dynamic hand gestures. This paper also presents an independent distributed multi state Gaussian probability model(IDMGPM) for recognition. In this system the average recognition rate is 97 8% on the training set and 95 6% on the testing set.
Keywords:Complex background  hand gesture segmentation  hand gesture recognition  independent distributed  multi  state Gaussian probability model
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号