首页> 外文会议>International Radar Conference >Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition
【24h】

Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition

机译:注意力增强卷积自动编码器,用于基于雷达的人类活动识别

获取原文

摘要

We propose an attention-augmented convolutional autoencoder for human activity recognition using radar micro-Doppler signatures. We use attention to overcome the limited receptive field of convolutional autoencoders (CAE), thereby enabling them to learn global information in addition to spatially localized features, while preserving their unsupervised pretraining characteristic. The augmentation is accomplished by concatenating convolutional local-feature maps with a set of attention feature maps that capture global dependencies. Using real data measurements of falls and activities of daily living, we demonstrate that the incorporation of the attention mechanism yields superior classification accuracy with respect to training sample size, compared to the conventional CAE.
机译:我们建议使用雷达微多普勒签名的人类活动识别增强注意的卷积自动编码器。我们利用注意力来克服卷积自动编码器(CAE)的有限接收领域,从而使他们能够在保留空间不受监督的预训练特性的同时,学习除空间局部化特征以外的全局信息。通过将卷积局部特征图与捕获全局依赖项的一组关注特征图进行级联来完成增强。使用跌倒和日常生活活动的真实数据测量,我们证明,与传统的CAE相比,并入注意机制在训练样本量方面产生了更高的分类准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号