|
|||||
|
|
| 一种可处理数据缺失的视角无关手语识别方法 | |
| 引用本文： | 王骐,陈熙霖,王春立,高文.一种可处理数据缺失的视角无关手语识别方法[J].计算机学报,2009,32(5). |
| 作者姓名： | 王骐 陈熙霖 王春立 高文 |
| 作者单位： | 1. 哈尔滨工业大学计算机科学与技术学院,哈尔滨,150001 2. 中国科学院计算技术研究所智能信息处理重点实验室,北京,100190 3. 大连海事大学信息科学与技术学院,辽宁,大连,116026 4. 中国科学院计算技术研究所智能信息处理重点实验室,北京,100190;北京大学信息科学与技术学院,北京,100871 |
| 基金项目： | 国家自然科学基金，多媒体与智能软件技术北京市重点实验室开放课题 |
| 摘 要： | 基于虚拟立体视假设,借鉴RANSAC技术的思想,文中针对数据缺失(帧对之间匹配特征可能较少)情况下的视角无关手语识别问题,提出一种Sample-Consensus方法.其基本出发点是,同一手语不同视角下的两个样本序列之间所有的对应帧对,可以解释为由某一虚拟立体视觉系统同步捕获,因而满足同一个基础矩阵,而且此基础矩阵能够基于部分对应帧对包含的点对应关系进行估计.实验表明,提出的Sample-Consensus方法能够有效地应用于数据缺失情况下的视角无关手语识别.另外,这种方法也可以扩展到相近的领域,如视角无关的动作识别和刚体运动分析等. |
| 关 键 词： | 手语识别 数据缺失 极线约束 随机抽样一致性方法 |
A Data-Deficiency-Tolerated Method for Viewpoint Independent Sign Language Recognition |
|
| WANG Qi,CHEN Xi-Lin,WANG Chun-Li,GAO Wen.A Data-Deficiency-Tolerated Method for Viewpoint Independent Sign Language Recognition[J].Chinese Journal of Computers,2009,32(5). | |
| Authors: | WANG Qi CHEN Xi-Lin WANG Chun-Li GAO Wen |
| Affiliation: | School of Computer Science and Technology;Harbin Institute of Technology;Harbin 150001;Key Laboratory of Intelligent Information Processing;Institute of Computing Technology;Chinese Academy of Sciences;Beijing 100190;School of Information Science & Technology;Dalian Maritime University;Dalian;Liaoning 116026;School of Electronics Engineering and Computer Science;Peking University;Beijing 100871 |
| Abstract: | This paper proposes a Sample-Consensus method for viewpoint independent sign language recognition under data deficiency(matched features are possibly deficient with regard to some frame pairs).The proposed method is based on the epipolar geometry and inspired by RANSAC.The basic idea is that all corresponded frames between two sequences of the same sign can be roughly considered as captured synchronously by a virtual stereo vision system and thus they will satisfy the same fundamental matrix.In addition,the... |
| Keywords: | sign language recognition data deficiency epipolar constraint RANSAC |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |