Human semantic segmentation facilitates the recognition of different parts of the human body and is essential for applications such as sports analysis and fall detection. To integrate human semantic segmentation into the domain of radio front-end sensing, this article introduces mmSeg, an innovative system that leverages commercial millimeter-wave radar for human semantic segmentation. However, the inherent propagation characteristics of mmWave signals often result in highly sparse point clouds with limited semantic information and the entanglement of temporal-topological features, making human semantic segmentation a challenging task. To address these challenges, mmSeg (i) first introduces a radar cross-section (RCS) calculation method suitable for commercial millimeter-wave radar to enhance the semantic information of radar point clouds at a coarse granularity; (ii) further designs a temporal-topological decoupling network to obtain the fine-grained human semantic segmentation results; (iii) constructs an efficient loss function for end-to-end training, based on an adjacency matrix graph to improve the segmentation performance. We evaluate mmSeg on our self-built millimeter-wave dataset HSS and a public dataset MM-Fi. mmSeg achieves an average point cloud segmentation accuracy of 87.74% on the HSS dataset and 84.18% on the MM-Fi dataset, outperforming the existing methods in both cases.

Millimeter-wave (mmWave) radar is emerging as a promising sensor for various human sensing tasks. Deep learning is frequently applied in radar-based applications, which typically require extensive data collection and labeling. In this demo, we present a low-cost hardware setup and a cross-platform software pipeline that automatically captures radar data of human activities, labels ground truth, and tests inference models in real time. The effectiveness of the testbed is demonstrated through real-time human pose estimation.

Tracking the human arm is essential for a variety of applications, including medical rehabilitation, sports analysis, and human-computer interaction. Current vision-based and wearable sensor-based approaches either struggle with occlusion, poor lighting conditions, and privacy concerns or result in intrusive user experiences. This paper introduces mmHAT, a novel 3D arm trajectory tracking method using mmWave radar. mmHAT proposes an end-to-end neural network design to address two major challenges: the lack of arm semantic information and dynamic variations in the mmWave point clouds. Firstly, mmHAT incorporates a multi-task joint learning framework, where the primary task is 3D arm tracking and the auxiliary task is gesture recognition. This aims to leverage the auxiliary task to guide the network in developing a deeper understanding of the user's arm movements. Secondly, for dynamic mmWave point clouds, mmHAT incorporates a new spatial-temporal feature encoder that aggregates the features of the arms point cloud from a global perspective. We collect ~320K frames of daily arm activity data for experimental validation. The results show that mmHAT achieves an average joint location error of 1.67 cm and angle estimation error of 4.23° for arm joints (i.e., elbow, wrist), while delivering excellent performance with only 2.67 ms latency.

This paper presents Mission, the first-of-this-kind cross-modal reidentification (ReID) design for mmWave Radar and RGB cameras. Given a person of interest detected by Radar in camera-restricted scenarios, Mission can identify the image of the person from cameras that are ubiquitously deployed in camera-allowed areas. We envision that cross Vison-RF ReID can significantly enrich mmWave human sensing with a wide spectrum of applications in security surveillance, tracking, and personalized services. Technically, we introduce a novel method for cross-modal similarity estimation that exploits inherent synergies between fine-grained 2D images and coarse-grained 3D Radar point clouds to effectively overcome their modal discrepancy. Through extensive experiments, we demonstrated that our proposed system can achieve 85% top-1 accuracy and 90% top-5 accuracy among 58 volunteers.

Abstract In group assessment, the focus is on finding high‐authority experts to improve the reliability of assessment results. In this study, we propose an authority updating algorithm while considering the power and judgement reliability of an expert on the basis of social networks and post‐evaluations. A network power index is established and used to reflect the power of an expert while considering social networks. The measurement of the judgement reliability of an expert considers the post‐evaluation of the objects selected by experts, thereby more scientifically reflecting the reliability of experts. The analysis shows the following: although the social‐network structure influences the authority of experts, the influence weakens when the assessment group is a highly or even fully connected group; the network effect may increase the authority of some experts and reduce that of others, and it will weaken as the network connectivity increases; moreover, the judgement reliability and authority of an expert while considering post‐evaluation can encourage him/her to make fair assessments and strive to reduce his/her motivation and cognitive biases.