Jiachen Zhu

Jiachen Zhu

Auto-generated profile, based on publicly available information

Jiachen Zhu

School of Artificial Intelligence, North China University of Science and Technology, Tangshan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
21 October 2024 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
JZJiachen Zhu
Jiachen Zhu
XHXiaohong Huang
Xiaohong Huang
ZDZhenmiao Deng
Zhenmiao Deng
YQYe Qiu
Ye Qiu
This article proposes a human pose recognition (HPR) system based on millimeter-wave (mmWave) radar (mRadHPRS). It includes an adaptive method for generating 3D point clouds of human bodies, a data augmentation method for sparse point clouds, and an HPR network based on mmWave radar (mmRadHPR). This study seeks to address a deficiency in current HPR research, which predominantly emphasizes various deep learning variants and often pays less attention to the accurate extraction of features from radar signals. The proposed system considers factors such as multipath effects in radar echoes and designs data augmentation methods tailored to the sparse distribution characteristics of mmWave radar point clouds. Additionally, a hierarchical point cloud processing network incorporating cross- and self-attention mechanisms is devised to extract human pose features. To evaluate the performance of the proposed model, we constructed a dataset with 10 different postures using mmWave radar. Experimental results demonstrate that the overall accuracy and average classification accuracy achieved by our method are 88.38% and 88.63%, respectively, significantly outperforming the three baseline methods. The system robustness experiment further validates the generalization ability and effectiveness of our approach.

1 April 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JZJiachen Zhu
Jiachen Zhu
XHXiaohong Huang
Xiaohong Huang
JLJiayu Liu
Jiayu Liu
ZDZhenmiao Deng
Zhenmiao Deng
In response to challenges posed by abnormal interference, such as target sidelobes within the reference window, this paper proposes a Sidelobe Suppression-Constant False Alarm Rate (SS-CFAR) detector. Drawing on the CLEAN concept, the SS-CFAR is designed for target detection in indoor environments with multiple targets using millimeter-wave radar. It employs second-order difference statistics combined with the Monte Carlo algorithm and iterative censoring to separate target signals from background clutter in radar echoes. Additionally, sidelobe suppression for the target is achieved by reconstructing the target’s echo information and the CLEAN concept. The simulation and actual experimental results demonstrate that SS-CFAR delivers superior detection performance, obviating the need for prior knowledge of anomalies or manual setting of parameters like the number of reference and guard cells, which traditionally depend on experiential adjustments. Compared to mean class and ordered statistics class CFAR detectors, SS-CFAR transcends reference window constraints. It accurately estimates background clutter, enhancing detection capabilities in multi-target environments. This innovative approach not only showcases superior detection performance and adaptability but also paves the way for the broader application of millimeter-wave radar in complex indoor scenarios.

1 January 2024 in Review of Scientific Instruments
Verified
Journal Article
Open access
PDF file
XHXiaohong Huang
Xiaohong Huang
JZJiachen Zhu
Jiachen Zhu
ZTZiran Tian
Ziran Tian
KXKunqiang Xu
Kunqiang Xu
YLyingchao Liu
yingchao Liu
The traditional algorithms for generating 3D human point clouds often face challenges in dealing with issues such as phantom targets and target classification caused by electromagnetic multipath effects, resulting in a lack of accuracy in the generated point clouds and requiring manual labeling of the position of the human body. To address these problems, this paper proposes an adaptive method for generating 3D human point clouds based on 4D millimeter-wave radar (Self-Adaptive mPoint, SA-mPoint). This method estimates the rough human point cloud by considering micro-motion and respiration characteristics while combining the echo dynamic with static information. Furthermore, it enhances the density of point cloud generation. It reduces interference from multipath noise through multi-frame dynamic fusion and an adaptive density-based clustering algorithm based on the center points of humans. The effectiveness of the SA-mPoint algorithm is verified through experiments conducted using the TI Millimeter Wave Cascade Imaging Radar Radio Frequency Evaluation Module 77G 4D cascade radar to collect challenging raw data consisting of single-target and multi-target human poses in an open classroom setting. Experimental results demonstrate that the proposed algorithm achieves an average accuracy rate of 97.94% for generating point clouds. Compared to the popular TI-mPoint algorithm, it generates a higher number of point clouds on average (increased by 87.94%), improves the average accuracy rate for generating point clouds (increased by 78.3%), and reduces the running time on average (reduced by 11.41%). This approach exhibits high practicality and promising application prospects.