Prediction of user ’ s intention based on the hand motion recognition
Prediction of user ’ s intention based on the hand motion recognition
复制标题
基于手部动作识别的用户意图预测
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
X. Clady
中科院分区：
文献类型：
--
作者：
Miguel Carrasco;X. Clady
文献中提出的大多数预测人类伸手抓握动作的方法都是采用被动方法设计的，即在用户面前使用相机。本文提出了一种利用计算机视觉方法来理解用户意图的新方法。我们的解决方案使用可穿戴系统进行手部运动估计。为了实现这样的系统，我们在手腕下安装了一个摄像头，从用户的角度捕捉动作。为了预测手的意图，我们通过隐马尔可夫模型框架来描述手的运动。结果表明，我们的系统可以在手到达物体之前预测物体的运动，平均准确率接近90%。
Most methods proposed in the literature for predicting movements involved in a reach-to-grasp action by human being are designed using passive methods, i.e, by using a camera in front of the user. A novel approach to understand the user’s intentions with computer vision methods is proposed in this paper. Our solution performs a hand motion estimation using a wearable system. To realize such system, we employ a camera beneath the wrist to capture motion from the user’s perspective. To predict hand intentions, we characterize a hand-movement trough a Hidden-Markov Model framework. As main result, our system can predict the movement before the hand can reach an object with a performance near to 90% in average.
DOI：
10.1007/11744023_32
发表时间：
2006-01-01
期刊：
COMPUTER VISION - ECCV 2006 , PT 1, PROCEEDINGS
影响因子：
--
作者：
Bay, Herbert;Tuytelaars, Tinne;Van Gool, Luc
通讯作者：
Van Gool, Luc