Figure - available from: Remote Sensing
This content is subject to copyright.
Source publication
Micro-Doppler signatures obtained from the Doppler radar are generally used for human activity classification. However, if the angle between the direction of motion and radar antenna broadside is greater than 60°, the micro-Doppler signatures generated by the radial motion of human body reduce significantly, thereby degrading the performance of the...
Citations
... These neural networks can achieve relatively high classification accuracy, which is achieved based on a large amount of data. Currently, there is a lot of research in this area, and by using mature datasets or collecting more data, the networks can adapt to the corresponding training results [18][19][20][21]. However, in practical application environments, considering the difficulties in data collection, most of the available training data is relatively limited. ...
With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%.
... Fahad Jibrin Abdu et al. proposed an efficient CCA-based feature fusion algorithm that effectively combines multi-deep CNN features of radar MD spectrograms [36]. Shahid Hassan et al. crafted a method for classifying human activity based on micro-Doppler and interferometric micro-motion signatures using a DCNN classifier [37]. ...
Human pose estimation (HPE) is an integral component of numerous applications ranging from healthcare monitoring to human-computer interaction, traditionally relying on vision-based systems. These systems, however, face challenges such as privacy concerns and dependency on lighting conditions. As an alternative, short-range radar technology offers a non-invasive, lighting-insensitive solution that preserves user privacy. This paper presents a novel radar-based framework for HPE, SCRP-Radar (space-aware coordinate representation for human pose estimation using single-input single-output (SISO) ultra-wideband (UWB) radar). The methodology begins with clutter suppression and denoising techniques to enhance the quality of radar echo signals, followed by the construction of a micro-Doppler (MD) matrix from these refined signals. This matrix is segmented into bins to extract distinctive features that are critical for pose estimation. The SCRP-Radar leverages the Hrnet and LiteHrnet networks, incorporating space-aware coordinate representation to reconstruct 2D human poses with high precision. Our method redefines HPE as dual classification tasks for vertical and horizontal coordinates, which is a significant departure from existing methods such as RF-Pose, RF-Pose 3D, UWB-Pose, and RadarFormer. Extensive experimental evaluations demonstrate that SCRP-Radar significantly surpasses these methods in accuracy and robustness, consistently exhibiting lower average error rates, achieving less than 40 mm across 17 skeletal key-points. This innovative approach not only enhances the precision of radar-based HPE but also sets a new benchmark for future research and application, particularly in sectors that benefit from accurate and privacy-preserving monitoring technologies.
... The Micro-Doppler signatures encompass frequency components derived from the translational motion of the body or the vibration and rotation of its non-rigid parts. These distinctive features can be directly exploited to identify various human activities [7][8][9]. ...
Developing accurate classification models for radar-based Human Activity Recognition (HAR), capable of solving real-world problems, depends heavily on the amount of available data. In this paper, we propose a simple, effective, and generalizable data augmentation strategy along with preprocessing for micro-Doppler signatures to enhance recognition performance. By leveraging the decomposition properties of the Discrete Wavelet Transform (DWT), new samples are generated with distinct characteristics that do not overlap with those of the original samples. The micro-Doppler signatures are projected onto the DWT space for the decomposition process using the Haar wavelet. The returned decomposition components are used in different configurations to generate new data. Three new samples are obtained from a single spectrogram, which increases the amount of training data without creating duplicates. Next, the augmented samples are processed using the Sobel filter. This step allows each sample to be expanded into three representations, including the gradient in the x-direction (Dx), y-direction (Dy), and both x- and y-directions (Dxy). These representations are used as input for training a three-input convolutional neural network-long short-term memory support vector machine (CNN-LSTM-SVM) model. We have assessed the feasibility of our solution by evaluating it on three datasets containing micro-Doppler signatures of human activities, including Frequency Modulated Continuous Wave (FMCW) 77 GHz, FMCW 24 GHz, and Impulse Radio Ultra-Wide Band (IR-UWB) 10 GHz datasets. Several experiments have been carried out to evaluate the model's performance with the inclusion of additional samples. The model was trained from scratch only on the augmented samples and tested on the original samples. Our augmentation approach has been thoroughly evaluated using various metrics, including accuracy, precision, recall, and F1-score. The results demonstrate a substantial improvement in the recognition rate and effectively alleviate the overfitting effect. Accuracies of 96.47%, 94.27%, and 98.18% are obtained for the FMCW 77 GHz, FMCW 24 GHz, and IR- UWB 10 GHz datasets, respectively. The findings of the study demonstrate the utility of DWT to enrich micro-Doppler training samples to improve HAR performance. Furthermore, the processing step was found to be efficient in enhancing the classification accuracy, achieving 96.78%, 96.32%, and 100% for the FMCW 77 GHz, FMCW 24 GHz, and IR-UWB 10 GHz datasets, respectively.
We have developed a versatile dataset generation system for hand gesture (HG) recognition using Frequency Modulated Continuous Wave (FMCW)-Multi Input Multi Output (MIMO) radar to improve the classification performance compared to conventional methods such as open dataset, other data generators using a generative adversarial network (GAN), and motion capture tools. The proposed system consists of an HG trajectory generator, an intermediate frequency (IF) signal generator corresponding to antenna locations, and a sampling timing generator without any open datasets or any motion capture data utilizing other sensors. After the training is performed by the generated dataset, the testing is carried out by actual data collected from FMCW-MIMO radar. Our findings show that the accuracy of 98% can be achieved with the generated dataset, and the proposed system is available for pre-training without using an actual dataset. Furthermore, when the mixed dataset is used for the training process, the accuracy improves by almost 37 points compared to when using the actual dataset only.
Telemedicine has the potential to improve access and delivery of healthcare to diverse and aging populations. Recent advances in technology allow for remote monitoring of physiological measures such as heart rate, oxygen saturation, blood glucose, and blood pressure. However, the ability to accurately detect falls and monitor physical activity remotely without invading privacy or remembering to wear a costly device remains an ongoing concern. Our proposed system utilizes a millimeter-wave (mmwave) radar sensor (IWR6843ISK-ODS) connected to an NVIDIA Jetson Nano board for continuous monitoring of human activity. We developed a PointNet neural network for real-time human activity monitoring that can provide activity data reports, tracking maps, and fall alerts. Using radar helps to safeguard patients’ privacy by abstaining from recording camera images. We evaluated our system for real-time operation and achieved an inference accuracy of 99.5% when recognizing five types of activities: standing, walking, sitting, lying, and falling. Our system would facilitate the ability to detect falls and monitor physical activity in home and institutional settings to improve telemedicine by providing objective data for more timely and targeted interventions. This work demonstrates the potential of artificial intelligence algorithms and mmwave sensors for HAR.
