Human Behavior Recognition Using Range-Velocity-Time Points

Human Behavior Recognition Using Range-Velocity-Time Points
复制标题

使用距离-速度-时间点进行人类行为识别

DOI:
10.1109/access.2020.2975676
复制
发表时间:
2020-02
期刊:
影响因子:
3.9
通讯作者:
TAO CHEN
TAO CHEN
中科院分区:
计算机科学3区
文献类型:
--
作者:
MENG LI;TAO CHEN

文献摘要

参考文献

相似文献

基于雷达的传感器不需要最佳的照明和大气条件,也不需要遮挡,这使它们成为复杂环境中人类行为分析的一种很有前途的解决方案。现有的基于雷达的模型通常从时间-速度域或时间-距离域检索特征。这种二维表示不能完全刻画动态人体运动特征。在本文中,我们提出了一种基于时间距离-多普勒点网的行为分析方法。我们将人的回声转换为3D点集,然后将其送入分层PointNet模型进行分类。与直接处理原始点云相比,本文提出的点网络能够更有效地从微动轨迹中学习结构特征。为了进一步提高模型在实际应用中的稳健性,我们设计了一个异常检测模块,用于检测多目标场景中的异常。在运动捕获数据库和距离-多普勒雷达测量上的实验结果表明,该方法在分类精度、噪声鲁棒性和异常检测精度方面都取得了优异的性能。
Radar-based sensors do not require optimal lighting and atmospheric conditions and nonocclusion, making them a promising solution for human behavior analysis in complex environments. Existing radar-based models generally retrieve features from either the time-velocity domain or the time-range domain. Such two-dimensional representations cannot fully depict dynamic human motion features. In this paper, we propose a temporal range-Doppler PointNet-based method to analyze human behavior. We transform human echoes to 3D point sets and then feed them into the hierarchical PointNet model for classification. The proposed point network can learn structural features from the micromotion trajectory more effectively than directly processing the raw point cloud. To further improve our model's robustness in practical applications, we design an outlier detection module for detecting anomalies such as in multitarget scenarios. The results of experiments on motion capture databases and range-Doppler radar measurements demonstrate that our method realizes outstanding performance in terms of the classification accuracy, noise robustness, and anomaly detection accuracy.
DOI: 10.1109/radar.2005.1435849
发表时间: 2005-05
期刊: IEEE International Radar Conference, 2005.
影响因子: --
作者:
Victor C. Chen
通讯作者: Victor C. Chen
DOI: --
发表时间: 2018-01
期刊: --
影响因子: --
作者:
Yangyan Li;Rui Bu;Mingchao Sun;Wei Wu;Xinhan Di;Baoquan Chen
通讯作者: Yangyan Li;Rui Bu;Mingchao Sun;Wei Wu;Xinhan Di;Baoquan Chen
DOI: --
发表时间: 2018-09
期刊: ArXiv
影响因子: --
作者:
Dan Hendrycks;Mantas Mazeika;Thomas G. Dietterich
通讯作者: Dan Hendrycks;Mantas Mazeika;Thomas G. Dietterich
DOI: 10.1016/j.patcog.2018.07.030
发表时间: 2019-01-01
影响因子: 8
作者:
Yang, Yang;Hou, Chunping;Xu, Jinchen
通讯作者: Xu, Jinchen
DOI: 10.1109/aps.2008.4619934
发表时间: 2008-07
期刊: 2008 IEEE Antennas and Propagation Society International Symposium
影响因子: --
作者:
S. S. Ram-S.;H. Ling
通讯作者: S. S. Ram-S.;H. Ling