arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09748cs.CVcs.AIcs.LGeess.IVeess.SP
收藏

基于惯性传感器的多域多模态融合人体动作识别

Multidomain Multimodal Fusion For Human Action Recognition Using Inertial Sensors

Ryerson University(瑞尔森大学)

Zeeshan Ahmad, Naimul Khan

摘要:

在动作识别过程中,多个动作的误分类的主要原因之一是提供动作的语义信息的互补特征的不可用。在不同的领域,这些特征以不同的尺度和强度存在。在现有的文献中,在不同的领域中独立地提取特征,但是融合这些多领域特征的好处没有实现。为了解决这一挑战,并提取完整的互补信息集,在本文中,我们提出了一种新的多域多模态融合框架,提取互补和不同的功能,从不同领域的输入模态。将输入的惯性数据转化为信号图像,然后分别采用离散傅立叶变换(DFT)和Gabor小波变换(GWT)将输入模态的空域信息变换到频域和时谱域,使输入模态具有多域和多模态特征。为了提高人体动作识别的准确性,采用卷积神经网络(CNN)提取不同领域的特征,然后采用典型相关融合(CCF)进行融合。三个惯性数据集上的实验结果表明,该方法的优越性相比,国家的最先进的。

英文摘要:

One of the major reasons for misclassification of multiplex actions during action recognition is the unavailability of complementary features that provide the semantic information about the actions. In different domains these features are present with different scales and intensities. In existing literature, features are extracted independently in different domains, but the benefits from fusing these multidomain features are not realized. To address this challenge and to extract complete set of complementary information, in this paper, we propose a novel multidomain multimodal fusion framework that extracts complementary and distinct features from different domains of the input modality. We transform input inertial data into signal images, and then make the input modality multidomain and multimodal by transforming spatial domain information into frequency and time-spectrum domain using Discrete Fourier Transform (DFT) and Gabor wavelet transform (GWT) respectively. Features in different domains are extracted by Convolutional Neural networks (CNNs) and then fused by Canonical Correlation based Fusion (CCF) for improving the accuracy of human action recognition. Experimental results on three inertial datasets show the superiority of the proposed method when compared to the state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑