In this letter, we propose a people counting method based on bi-motion-model-framework (BMMF) using ultra-wide bandwidth (UWB) radar. Because different people motion states (people standing still or moving) in indoor environments lead to significant fluctuations of the received radar signal, it will confuse the results of different cases and degrade the estimation accuracy of the people counting methods. Herein, we first attempt to extract the motion features, including activation index (AI), connected regions (CRs), and energy of frames (EoF), to distinguish the motion states of people. Then, we use the probabilistic model (PM) method or convolutional neural network (CNN) method to predict the number of people for the classified motion state model. Finally, the experimental results show that the proposed method significantly outperforms the PM-based and CNN-based methods without considering the motion states influences.

In this paper, we propose a novel people counting algorithm exploiting convolutional neural network (CNN) using a low radiation impulse radio ultra-wide bandwidth (IR-UWB) radar. Because of the ever-changing signals caused by the various cases of human motion scales, superposition and obstruction of signals as well as the attenuate of signal's strength along the distance and the angle, it is not easy to handle the people counting task by directly detecting targets for each range bin. Thus, we hope to excavate the information of targets' patterns, including their densities and forms of patterns' distributions in the detecting region to execute the counting task. To achieve this, the multi-scale range-time maps are extracted from the received data and further used to classify the number of people using the CNN. Finally, the experiments are conducted to show the priority of the proposed algorithm.

本文为弥补基于传感器方法的检测系统存在的不足,基于低辐射UWB雷达系统设计了一套室内人员边缘检测系统.本系统可对少数目标情况下(目标数≤2)的人员进行有效跟踪;人员数目估计精度(含错误±1)可达95％以上;日常活动识别分类精度可达86％.

近年来,随着智能物联网应用的快速发展,雷达传感器由于具有保护隐私、全天候全天时工作、不受光线和遮挡影响等优点,在人体目标日常行为活动识别方面受到了学术界和产业界的极大重视.针对一种超低辐射的超宽带雷达(Impulse Radio Ultra-Wideband,IR-UWB),提出了一种室内人员日常活动(包含静止、坐下、走路、起立)分类方法.该方法首先利用目标检测方法检测出目标有效距离单元;其次,提出了基于平均多普勒频率、信息量和多普勒能量的3种微多普勒特征进行动静目标粗分类;最后,采用长短期记忆神经网络(Long Short-Term Memory,LSTM)对人体活动进行细分类.实验结果表明,人体活动细分类的平均准确率能达到92.52％.

In this paper, we propose an cascaded spatial-temporal three-stages (CSTTS) detector for short-range human detection using mono-static ultra-wideband (UWB) radar. The key technical difficulty is how to improve the detection performance of relatively remote or slow speed targets in strong clutter environments. To solve this problem, the proposed detector can be divided into three stages: firstly, we do the outliers detection along the temporal dimension according to an adaptive updated environment clutter's maps; then we use a log-normal order-statistical constant-false-alarm-rates (OS-CFAR) detector to set a series of thresholds along the spatial dimension (i.e. different range bins); finally an accumulative detector is applied to remove a few false alarms. Experiment results show the improved performance of the proposed CSTTS detector for relatively remote and slow speed targets.

Clutter suppression, especially in time-varying environments is a hindrance that must be solved for radar systems applied to unmanned vehicles. However, exponential moving average (EMA) method, a common background subtraction technique, does not handle such a situation very well because the fixed parameter constrains the updating of the estimated clutter. In this paper, we propose a novel adaptive clutter suppression algorithm to adjust the parameter of EMA method under the background of time-varying clutter. The main idea is to adopt a low-complexity time-averaged variable forgetting factor (TAVFF) mechanism. The proposed algorithm is assessed with data recording measured background clutter and a simulated moving target. The simulation results demonstrate our proposed algorithm has achieved both fast convergence and good steady-state performance.