• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>電子情報通信学会技術研究報告. パターン認識·メディア理解. Pattern Recognition and Media Understanding >Realtime gesture recognition by learning and selective control of visual interest points
【24h】

Realtime gesture recognition by learning and selective control of visual interest points

机译：通过学习和选择性控制视觉兴趣点进行实时手势识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recognition techniques of human gestures are indispensable in designing interaction systems which respond to user's non-verbal information in real-time. Most of traditional approaches neglected the problem of slow and unstable processing speed caused by increasing number of target gestures and fluctuating load of real-time applications such as virtual reality. This paper deals with the above-mentioned problems by introducing a selective control method for visual interest points. To demonstrate the applicability of the proposed methods, a gesture video system and a sign language image database retrieval system were developed. Evaluation results strongly indicate the effectiveness of the proposed methods.
机译：在设计可实时响应用户非语言信息的交互系统时，人体手势的识别技术必不可少。大多数传统方法都忽略了由于目标手势数量增加以及诸如虚拟现实之类的实时应用程序的负载波动而导致处理速度缓慢和不稳定的问题。通过引入视觉兴趣点的选择性控制方法来解决上述问题。为了证明所提出方法的适用性，开发了手势视频系统和手语图像数据库检索系统。评估结果强烈表明了所提出方法的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号