Position-Information-Indexed Classifier for Improved Through-Wall Detection and Classification of Human Activities Using UWB Bio-Radar
Position-Information-Indexed Classifier for Improved Through-Wall Detection and Classification of Human Activities Using UWB Bio-Radar
复制标题
使用 UWB 生物雷达改进人类活动的穿墙检测和分类的位置信息索引分类器
DOI：
10.1109/lawp.2019.2893358
复制
发表时间：
2019-03-01
影响因子：
4.2
通讯作者：
Wang, Jianqi
中科院分区：
文献类型：
--
作者：
Qi, Fugui;Liang, Fulai;Wang, Jianqi
基于超宽带（UWB）生物雷达的微多普勒特征（MD）对人体活动进行非接触穿透检测和分类在灾后搜救和城市军事行动等各种实际应用中具有重要意义。然而，对于所有的分类器，在不同位置的不同幅度的活动的MD功能很可能会导致分类错误，由于MD衰减和混乱。本文提出了一种基于位置信息索引的分类器改进方法。它旨在提高各种分类器在识别和分类方面的性能。该方法充分利用超宽带生物雷达获取的位置信息，建立一个位置标记的模块化MD特征数据库。它还指导搜索自适应的最佳预测子模型的PIIC的活动分类在一个随机的位置。我们报告的穿墙检测和分类实验结果有关的5个活动范围内的6米。这些结果，基于四个典型的分类器，表明基于PIIC的分类器可以有效地避免这些分类错误。此外，所有基于PIIC的分类器呈现出更好的分类性能，与基于整体模型的分类器相比，平均准确率提高了8.16%。这些性能评估实验表明，该方法具有很强的鲁棒性和稳定性，对各种分类器具有广泛的适用性。
Noncontact penetrating detection and classification of human activities based on micro-Doppler signatures (MDs) using ultrawideband (UWB) bio-radars are valuable tasks in various practical applications such as post-disaster search-and-rescue operations and urban military operations. However, for all classifiers, MD features of different-magnitude activities at different positions are likely to result in classification errors due to MD attenuation and confusions. This letter proposes a classifier improving method called position-information-indexed classifier (PIIC). It aims at enhancing the performance of various classifiers in terms of recognition and classification. This method fully exploits the position information acquired by UWB bio-radar to create a position-labeled modularized database of MD features. It also guides searching adaptively for optimal predict submodel of PIICs for activity classification at a random position. We report through-wall detection and classification experimental results related to five activities within a range of 6 m. These results, based on four typical classifiers, demonstrate that PIIC-based classifiers can avoid those classification errors in an effective manner. Moreover, all PIIC-based classifiers present a better classification performance with an average accuracy rise of 8.16% compared with those of overall-model-based classifiers. These performance evaluation experiments suggest that this method is strongly robust and stable, presenting wide applicability to various classifiers.