Ke Zhang

Ke Zhang

Auto-generated profile, based on publicly available information

Ke Zhang

Changsha University of Science and Technology

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 June 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YSYongkun Song
Yongkun Song
TYTianxing Yan
Tianxing Yan
KZKe Zhang
Ke Zhang
XLXian Liu
Xian Liu
YDYongpeng Dai
Yongpeng Dai
JTJin Tian
Jin Tian
Human action recognition (HAR) methods based on ultra-wideband (UWB) multiple-input multiple-output (MIMO) radar have demonstrated substantial potential in complex environments. However, the use of single-modal data, such as spectrograms or point clouds, poses significant limitations; it is easy to get confused when dealing with similar actions, particularly in challenging scenarios. To overcome these limitations, this study proposes an action recognition approach that leverages bimodal data and spatiotemporal features for improved performance. Four-dimensional radar image data of the human body are captured using UWB MIMO radar and processed into four-dimensional point cloud data and four-dimensional intensity projection image data, which collectively serve as bimodal feature inputs. To process these bimodal feature data, a network architecture named Point Image Fusion-Net (PIF-Net) is developed, incorporating spatiotemporal sequence classification to achieve recognition of human actions. The network initially extracts spatial features from the bimodal feature data, followed by temporal feature extraction, culminating in the classification of spatiotemporal features. Experimental results show that the proposed method achieves an accuracy of 96.75% in action recognition tasks, validating the approach.

18 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YSYongkun Song
Yongkun Song
KZKe Zhang
Ke Zhang
TYTianxing Yan
Tianxing Yan
JTJin Tian
Jin Tian
YDYongpeng Dai
Yongpeng Dai
TWTao Wang
Tao Wang
This paper proposes a multimodal human pose re-construction method based on 3D ultra-wideband (UWB) radar images and point clouds, aiming to improve the accuracy of human pose estimation through the fusion of radar images and point cloud data. First, a UWB 3D imaging radar system is designed, which synchronously collects radar echo signals and optical images, con-structing a multimodal dataset covering various common actions and different human characteristics. Radar data processing in-cludes azimuth-range 2D imaging, target locking, local 3D imag-ing, discrete sampling, and maximum projection to generate point cloud data and projection images. Optical image processing uses mature methods to reconstruct 3D poses as pose labels for point clouds and projection images. To achieve multimodal data fusion, the UWB FusionPose network is designed, comprising an image feature extraction network, a point cloud feature extraction net-work, and a pose reconstruction network. The image feature ex-traction network is based on the ResNet-18 framework, while the point cloud feature extraction network adopts a pyramid struc-ture. After feature fusion, a multi-layer perceptron (MLP) is used to predict human pose information. Additionally, this paper ex-plores the impact of fusion parameters on network performance and verifies the effectiveness of the multimodal network through ablation experiments. Experimental results show that this method effectively utilizes radar point cloud data and projection image data to accurately reconstruct the 3D pose of human targets. This research not only provides a new human pose reconstruction tech-nique but also offers valuable references for the future develop-ment of radar imaging technology and multimodal data fusion methods.

19 July 2026
Verified
Book Chapter
Open access
PDF file
YSYongkun Song
Yongkun Song
KZKe Zhang
Ke Zhang
XLXian Liu
Xian Liu
QYQingrong Yang
Qingrong Yang
TYTianxing Yan
Tianxing Yan
Ultra-Wideband Multiple-Input Multiple-Output (UWB MIMO) radar shows great potential in non-contact 3D human pose estimation due to its penetration, privacy protection and all-weather capabilities. However, varying Radar Cross Section (RCS) across human body parts causes severe spatial density inhomogeneity in radar point clouds. Existing methods using uniform sampling and global feature aggregation often lose critical features of distal limbs, damage point cloud spatial topology, and lead to semantic-geometric misalignment. Additionally, the lack of biomechanical constraints results in insufficient anatomical rationality and practical usability of estimated poses. To address these challenges, we propose an end-to-end Semantic-Geometric Alignment Network (SGA-Net). It integrates three core designs: density-aware spatial (DAS) encoder, Cross-Attention Bridge (CAB) module, and data-driven biomechanical loss function, achieving accurate semantic-geometric feature alignment and robust 3D pose estimation. Experimental results show that our method achieves a Mean Per Joint Position Error (MPJPE) of 29.95 mm, significantly outperforming existing baselines. This work provides a feasible technical paradigm for highly robust edge-side behavior monitoring in privacy-sensitive scenarios.