Recognition of shape-changing hand gestures based on switching linear model
Recognition of shape-changing hand gestures based on switching linear model
复制标题
基于切换线性模型的变形手势识别
DOI：
10.1109/iciap.2001.956979
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
Y. Shirai
中科院分区：
文献类型：
--
作者：
Mun;Y. Kuno;N. Shimada;Y. Shirai
提出了一种同时跟踪和识别变形手势的方法。使用活动轮廓模型的切换线性模型很好地对应于手的时间形状和运动。切换线性模型中的推理在计算上是困难的，因此学习过程不能通过精确的EM(期望最大化)算法来执行。然而，我们提出了一种使用折叠方法的近似EM算法，在该方法中，将一些高斯合并成一个单一的高斯。跟踪通过基于卡尔曼滤波的前向算法和折叠方法来实现。我们还提出了正则化平滑，它起到了减少状态向量训练序列之间的跳跃变化的作用，以应对复杂多变的手形。在执行跟踪时，通过从一些学习的模型中选择具有最大似然的模型来执行识别处理。给出了几种变形手势的实验结果。
We present a method to track and recognise shape-changing hand gestures simultaneously. The switching linear model using the active contour model corresponds well to temporal shapes and motions of hands. Inference in the switching linear model is computationally intractable and therefore the learning process cannot be performed via the exact EM (expectation maximization) algorithm. However, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present the regularized smoothing, which plays a role in reducing jump changes between the training sequences of state vectors to cope with complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some learned models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.