Papers
12
Total Citations
515
H-Index
7
About
Peijun Zhao is a researcher whose work sits at the intersection of mobile sensing, deep learning, and autonomous navigation, with particular focus on inertial navigation, millimeter-wave (mmWave) radar, and LiDAR-based localization. His most influential contribution, "Deep-Learning-Based Pedestrian Inertial Navigation" (2020, 154 citations), demonstrated how neural networks could transform raw IMU data into reliable pedestrian positioning for IoT applications. Complementing this, his OxIOD dataset (2018, 60 citations) provided the research community with a foundational resource for training and benchmarking inertial odometry systems. Zhao's milliEgo framework (2020, 130 citations) pushed the boundaries of robust egomotion estimation by fusing single-chip mmWave radar with deep sensor fusion, offering a compelling alternative to vision-dependent methods. His work on mmWave radar extends to health monitoring, with contactless heart rate sensing via robot-mounted radar (2020, 70 citations), and precise 3D drone motion capture (2021, 22 citations). His PointLoc framework (2021, 54 citations) further advanced LiDAR-based 6-DoF pose regression without requiring pre-built maps. Most recently, Zhao has explored smartphone-powered rehabilitation systems, reflecting a broadening commitment to accessible, real-world human-centered technology.
Research Focus
Key Achievements
Top Papers
- 1
- 2milliEgo130 citations · 2020
- 3Heart Rate Sensing with a Robot Mounted mmWave Radar70 citations · 2020
- 4OxIOD: The Dataset for Deep Inertial Odometry60 citations · 2018
- 5PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization54 citations · 2021
- 6
- 7
- 8PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization5 citations · 2020
- 9
- 10Enabling Home Rehabilitation with Smartphone-Powered Upper Limb Training2 citations · 2024