Open-set human activity recognition based on micro-Doppler signatures
Open-set human activity recognition based on micro-Doppler signatures
复制标题
DOI：
10.1016/j.patcog.2018.07.030
复制
发表时间：
2019-01-01
影响因子：
8
通讯作者：
Xu, Jinchen
中科院分区：
文献类型：
--
作者：
Yang, Yang;Hou, Chunping;Xu, Jinchen
由于活动的复杂性，开集活动识别仍然是一个具有挑战性的问题。在以往的工作中，人们已经付出了大量的努力来构造负集或为目标集设置最优阈值。本文提出了一种基于产生式对抗性网络(GAN)的模型，称为Open-GAN，用于解决训练过程中无需人工干预的开集识别问题。生成器产生假目标样本，作为自动否定集，鉴别器被重新设计以输出多个类别和一个未知的类别。我们在测量的微多普勒雷达数据集和卡内基梅隆大学(CMU)的运动捕获(MOCAP)数据库上对该方法的有效性进行了评估。与几种先进方法的比较结果表明，OpenGAN为人类活动识别提供了一种很有前途的开集解决方案，即使在已知类很少的情况下也是如此。消融研究也被执行，结果表明，所提出的结构优于其他变种，并且在两个数据集上都是健壮的。(C)2018爱思唯尔有限公司。保留所有权利。
Open-set activity recognition remains as a challenging problem because of complex activity diversity. In previous works, extensive efforts have been paid to construct a negative set or set an optimal threshold for the target set. In this paper, a model based on Generative Adversarial Network (GAN), called 'Open-GAN' is proposed to address the open-set recognition without manual intervention during the training process. The generator produces fake target samples, which serve as an automatic negative set, and the discriminator is redesigned to output multiple categories together with an 'unknown' class. We evaluate the effectiveness of the proposed method on measured micro-Doppler radar dataset and the MOtion CAPture (MOCAP) database from Carnegie Mellon University (CMU). The comparison results with several state-of-the-art methods indicate that OpenGAN provides a promising open-set solution to human activity recognition even under the circumstance with few known classes. Ablation studies are also performed, and it is shown that the proposed architecture outperforms other variants and is robust on both datasets. (C) 2018 Elsevier Ltd. All rights reserved.