激光与光电子学进展, 2020, 57 (2): 021009, 网络出版: 2020-01-03   

基于卷积神经网络的雷达人体动作与身份多任务识别 下载: 1320次

Human Activity and IdentityMulti-Task Recognition Based on Convolutional Neural Network Using Doppler Radar
作者单位
天津大学电气自动化与信息工程学院, 天津 300072
摘要
为弥补单任务识别未充分利用相关任务监督信息的缺陷,提出了一种基于卷积神经网络的多任务识别模型。该模型引入注意力机制,对任务共享层的特征进行重校正,并结合多尺度结构进行特征融合,最后在任务特定层上进行多任务识别。针对共享特征空间内类分布不紧凑导致的模型泛化性能降低问题,本文在模型中引入中心损失函数与均方误差损失函数,与传统的交叉熵损失函数相结合,共同优化模型。实验结果表明:所提模型在人体6个动作类别和15个身份类别上的最高识别准确率分别可达100%和99.93%,两种任务上识别的总准确率可达99.93%,均优于任务独立识别时的各项准确率,说明所提模型能更有效地同时完成人体动作及身份识别任务。
Abstract
A multitask recognition model based on convolutional neural network is proposed to avoid single task recognition ignoring supervision information of related tasks. The proposed model introduces an attention mechanism to perform feature recalibration of the task shared layer and combines the multiscale structure for feature fusion. Finally, multi-task recognition is performed on the task-specific layers. Center loss and mean square error loss functions are employed together with the traditional cross entropy loss function to solve the generalization degradation problem caused by uncompact class distribution in the shared feature space. Experimental results on 6 human activities and 15 identities show that the model can achieve the maximum recognition accuracies of 100% and 99.93% on each task, respectively, and the multitask accuracy is up to 99.93%. The results are better than those obtained by the single task models. This shows that the model can simultaneously perform human activity and identity recognition more effectively.

侯春萍, 蒋天丽, 郎玥, 杨阳. 基于卷积神经网络的雷达人体动作与身份多任务识别[J]. 激光与光电子学进展, 2020, 57(2): 021009. Hou Chunping, Jiang Tianli, Lang Yue, Yang Yang. Human Activity and IdentityMulti-Task Recognition Based on Convolutional Neural Network Using Doppler Radar[J]. Laser & Optoelectronics Progress, 2020, 57(2): 021009.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!