Gesture recognition using hybrid generative-discriminative approach with Fisher Vector
Gesture recognition using hybrid generative-discriminative approach with Fisher Vector
复制标题
DOI：
10.1109/icra.2015.7139614
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
Yusuke Goutsu;W. Takano;Yoshihiko Nakamura
中科院分区：
文献类型：
--
作者：
Yusuke Goutsu;W. Takano;Yoshihiko Nakamura
手势识别被用于许多实际应用，如人机交互、医疗康复和手语。本文采用Fisher向量混合生成-判别方法来提高识别性能。该策略是将处理时空运动数据的隐马尔可夫模型的生成方法与关注分类任务的支持向量机判别方法相结合。将运动段编码为hmm，并将每段转换为FV， FV的元素可以作为hmm生成的段的概率对其参数的导数来获得。SVM随后由fv进行训练。支持向量机可以将输入手势分类到相应的手势类别中。在实验中，我们通过比较三种HMM链模型和四种分类方法来测试我们的方法，这些方法是在ChaLearn Looking at People Challenge 2014 （LAP 2014）提供的数据集上进行的。结果表明，相似的手势模式被紧密地聚在几个类别中。我们基于从左到右hmm的方法优于其他手势识别方法。更具体地说，混合生成-判别方法克服了标准HMM方法，生成核方法克服了生成嵌入方法。从这些结果来看，我们的方法可以有效地提高识别性能。
Gesture recognition is used for many practical applications such as human-robot interaction, medical rehabilitation and sign language. In this paper, we apply a hybrid generative-discriminative approach by using the Fisher Vector to improve the recognition performance. The strategy is to merge the generative approach of Hidden Markov Model dealing with spatio-temporal motion data with the discriminative approach of Support Vector Machine focusing on the classification task. The motion segments are encoded into HMMs, and each segment is converted to FV, whose elements can be obtained as the derivative of the probability of the segment being generated by the HMMs with respect to their parameters. SVM is subsequently trained by the FVs. An input gesture can be classified to corresponding gesture category by SVM. In the experiments, we test our approach by comparing three HMM chain models and four categorization methods on dataset provided by the ChaLearn Looking at People Challenge 2014 (LAP 2014). The results show that similar gesture patterns are clustered closely in several categories. Our approach based left-to-right HMMs outperforms other gesture recognition methods. More specifically, the hybrid generative-discriminative approach overcomes the standard HMM approach and the generative kernel approach overcomes the generative embedding approach. For these results, our approach is effective to improve the recognition performance.