The HMM-Based Sensing Correction Method for Leap Motion Finger Tracking
The HMM-Based Sensing Correction Method for Leap Motion Finger Tracking
复制标题
基于HMM的跳跃运动手指跟踪传感校正方法
DOI：
10.1109/icice49024.2019.9117461
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Tsung
中科院分区：
文献类型：
--
作者：
Lien;Tsung
Leap Motion 是一种快速、高精度的手指跟踪光学传感器。然而，当手指和手掌相互重叠时，它有局限性。在这种情况下，前部遮挡了后部，使后部无法被观察到，从而产生传感误差。这项研究提出了一种从 Leap Motion 盲区进行纠错的新方法。所提出的方法侧重于使用隐马尔可夫模型（HMM）进行手指方向的数据校正。 Leap Motion捕获的数据是时间序列数据集，手指运动模型的行为与HMM（双随机过程）的特性完全相似。每个隐藏状态代表一个手指运动区域的空间。通过维特比算法，可以识别手指的准确区域。测试数据由每个状态的手指张开运动和手指闭合运动组成，形成混淆矩阵，表明识别率显着提高。所有 ACC、TPR 和 FPR 都比直接从 Leap Motion 观察到的要好。所提出的方法表明，HMM可以减轻盲区的障碍，并在没有太多延迟的情况下提高手指跟踪的正确率。这对于盲区精度要求较高的手势控制场景很有帮助。合适的应用之一是拟人机器人手控制。所提出的方法能够正确捕获手指运动。正因如此，拟人机械手才能得到很好的控制。
Leap Motion is a fast and high accuracy optical sensor for finger tracking. However, it has limitation when fingers and palm lapped over each other. In this scenario, the front part sheltered rear part and makes the rear part unobservable to yield sensing error. This study proposes a novel method for error correction from the blind zone of Leap Motion. The proposed method focuses on data correction of finger direction by using Hidden Markov Model (HMM). Data captured from Leap Motion is a time series data set and the finger movement model behavior exactly similar to the characteristic of HMM (doubly stochastic process). Each of hidden states stands for a space of finger movement region. Through Viterbi algorithm, the exact region of the finger can be identified. The test data consists of finger-opened movement and finger-closed movement for each state, which create confusion matrix that indicated the recognition rate have significantly improved. All the ACC, TPR and FPR are better than directly observed from Leap Motion. The proposed method shows that HMM can alleviate the obstacle of the blind zone and increase the correct rate of finger tracking without much delay. That is helpful for the scenario of gesture control that needed much accuracy in the blind zone. One of the appropriate application is anthropomorphic robotic hand control. The proposed method is able to capture the finger movement correctly. For this reason, anthropomorphic robotic hand can be controlled well.