The scarcity of high-quality millimeter-wave (mmWave) radio frequency (RF) data for human sensing poses significant challenges to the generalization and robustness of deep learning models in this domain. The acquisition of RF data is constrained by the need for specialized equipment and specific application scenarios, resulting in a significant gap in both quantity and diversity compared to visual data. To address this critical bottleneck, we propose PODM-mmHPE, a novel framework that leverages Physical Optics (PO) and Diffusion Models (DM) to synthesize high-quality human RF data for mmWave Human Pose Estimation (mmHPE). Our framework introduces two key innovations: (1) a PO-based RF simulation pipeline that generates coarse RF data from 3D human mesh models by modeling electromagnetic wave interactions with body surface geometry and (2) a DM-based refinement module that transforms the coarse data into realistic RF heatmaps, capturing the complexity and noise of real-world RF signals. Furthermore, we develop map2pose, a Graph Convolutional Network (GCN)-based model that establishes an end-to-end mapping from RF heatmaps to 3D human poses, serving both as a downstream task benchmark and a validation mechanism for the quality of our synthetic data. Experiments demonstrate PODM-mmHPE’s effectiveness with 23.9% and 25.1% MPJPE reductions on HuPR and mmHPE datasets under synthetic augmentation. This validates our physics-guided synthesis enables generalizable mmWave pose estimation.

In the realm of autonomous driving, precise and robust 3D perception is paramount. Multi-modal fusion for 3D object detection is crucial for improving accuracy, generalization, and robustness in autonomous driving. In this paper, we introduce the Depth Enhancement Network (DEN), an innovative camera-radar fusion framework that generates an accurate depth estimation for 3D object detection. To overcome the lack of spatial information To overcome the limitations caused by the lack of spatial information in an image, DEN estimates image depth using accurate radar points. Furthermore, to extract more comprehensive and fine-grained scene depth information, we present an innovative label optimization strategy that enhances label density and quality. DEN achieves an 18.78% reduction in Mean Absolute Error (MAE) and a 12.8% decrease in Root Mean Square Error (RMSE) for depth estimation. Additionally, it improves 3D object detection accuracy by 0.8% compared to the baseline model. Under low visibility conditions, DEN demonstrates a 6.7% reduction in MAE and a 9.6% reduction in RMSE compared to the baseline. These improvements demonstrated its robustness and enhanced performance under challenging conditions.

Nowadays, human pose estimation (HPE) is widely used in several application areas. The current mainstream method based on vision suffers from privacy leakage and relies on lighting conditions. To adopt a more privacy-preserving and pervasive HPE approach, recent studies have implemented 3-D HPE using commodity radio frequency (RF) signals. However, RF-based HPE faces issues, such as resolution limitations and complex data processing, which makes it challenging to extract and utilize multiscale human activity features. In this article, we propose mmHPE, a novel approach to detect and reconstruct 3-D human posture in multiscale scenarios using a single millimeter wave radar. mmHPE consists of three main parts. Specifically, we develop a 3-D target detection network (TDN) and design an optimized loss function for it to enhance its 3-D target bounding box (BBox) detection capability in radar 3-D space. Next, an enhanced point cloud generator (EPCG) algorithm based on the 3-D target BBox is proposed to generate a stable and accurate point cloud of the target. Furthermore, we design a multiscale coarse-fine HPE network (CFN) ranging from approximate to precise estimation for reconstructing a 3-D skeleton from point cloud data. Extensive experiments demonstrate that our method surpasses other methods for 3-D human pose reconstruction in multiscale scenes, with an average error of 4.50 cm. Our method is robust enough to accurately estimate the target pose even in occluded or low-light scenes.

In this paper, we introduce mmOrbit, a mmWave-based rotor orbit measurement system that can estimate rotor orbit by analyzing machinery surface vibration. To measure the 2D rotor orbit, two synchronized mmWave radars are deployed to build the orbit from different viewpoints. The existing literature shows that the micro-displacement measurement accuracy of mmWave radar is not enough to meet the application requirements of micron-level resolution without appropriate fine-gained processing methods. Therefore, we propose a three-step vibration displacement extraction algorithm with sliding table to extract mechanical vibration micro-displacement and increase measurement precision. Accurate mechanical vibration displacements in two vertical directions are used to estimate the 2D rotor orbit. Our extensive experiments indicate that mmOrbit can accurately measure mechanical vibration micro-displacement with an error of 4.4 μm for the 80th percentile. Furthermore, mmOrbit can estimate 2D rotor orbit with high precision, showing an orbit eccentricity error of 7%, an orbit direction error of 7 °, and a disjoint area proportion of 17% for the 80th percentile. The imbalance detection experiment verifies the accuracy and dependability of our measured rotor orbit.

Non-invasive human vital sign detection has gained significant attention in recent years, with its potential for contactless, long-term monitoring. Advances in radar systems have enabled non-contact detection of human vital signs, emerging as a crucial area of research. The movements of key human organs influence radar signal propagation, offering researchers the opportunity to detect vital signs by analyzing received electromagnetic (EM) signals. In this review, we provide a comprehensive overview of the current state-of-the-art in millimeter-wave (mmWave) sensing for vital sign detection. We explore human anatomy and various measurement methods, including contact and non-contact approaches, and summarize the principles of mmWave radar sensing. To demonstrate how EM signals can be harnessed for vital sign detection, we discuss four mmWave-based vital sign sensing (MVSS) signal models and elaborate on the signal processing chain for MVSS. Additionally, we present an extensive review of deep learning-based MVSS and compare existing studies. Finally, we offer insights into specific applications of MVSS (e.g., biometric authentication) and highlight future research trends in this domain.

BACKGROUND: DNA barcoding technology, which uses a short piece of DNA sequence to identify species, has wide ranges of applications. Until today, a universal DNA barcode marker for plants remains elusive. The rbcL and matK regions have been proposed as the "core barcode" for plants and the ITS2 and psbA-trnH intergenic spacer (PTIGS) regions were later added as supplemental barcodes. The use of PTIGS region as a supplemental barcode has been limited by the lack of computational tools that can handle significant insertions and deletions in the PTIGS sequences. Here, we compared the most commonly used alignment-based and alignment-free methods and developed a web server to allow the biologists to carry out PTIGS-based DNA barcoding analyses. RESULTS: First, we compared several alignment-based methods such as BLAST and those calculating P distance and Edit distance, alignment-free methods Di-Nucleotide Frequency Profile (DNFP) and their combinations. We found that the DNFP and Edit-distance methods increased the identification success rate to ~80%, 20% higher than the most commonly used BLAST method. Second, the combined methods showed overall better success rate and performance. Last, we have developed a web server that allows (1) retrieving various sub-regions and the consensus sequences of PTIGS, (2) annotating novel PTIGS sequences, (3) determining species identity by PTIGS sequences using eight methods, and (4) examining identification efficiency and performance of the eight methods for various taxonomy groups. CONCLUSIONS: The Edit distance and the DNFP methods have the highest discrimination powers. Hybrid methods can be used to achieve significant improvement in performance. These methods can be extended to applications using the core barcodes and the other supplemental DNA barcode ITS2. To our knowledge, the web server developed here is the only one that allows species determination based on PTIGS sequences. The web server can be accessed at http://psba-trnh-plantidit.dnsalias.org.

Video object segmentation is a critical first step in virtual advertisement system. In this paper, we present belief propagation based method to increase the accuracy and efficiency of segmentation. The background color models are built as a mixture of a global color model and a per-pixel color model, while foreground color likelihood is modeled by spatially global Gaussian Mixture, and a realistic model of shadow effects is built also. The neighborhood dependencies are built with a MRF prior. Belief propagation is used to compute the marginal probability in MRF, and the video objects are segmented effectively. Experiment results show that the algorithm has the good performance, and has been used in our virtual advertisement system.

Fast and reliable detection of moving objects is one of the important requirements for video surveillance systems. Mean shift based non-parametric background modeling supports more sensitive and robust detection in dynamic outdoor scenes. However it is prohibitive for real-time applications such as video surveillance. This paper aims to deal with the limitation of high computational complexity. Firstly, coarse to fine method are proposed to avoid raster scanning entire image. Foreground pixels are detected in coarse level to roughly locate the foreground objects in the image, and then finer detection is performed on the corresponding blocks gradually. Secondly, fast mean shift approach is presented according to temporal dependencies. Mean shift iterations are performed starting from incoming data and the mode found in last time. The experimental results show that the proposed algorithm is effective and efficient in dynamic environment.