A5102022704- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Image and Object Detection Techniques
- Advanced SAR Imaging Techniques
- Advanced Semiconductor Detectors and Materials
- Industrial Vision Systems and Defect Detection
- Microwave Imaging and Scattering Analysis
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Radiation Detection and Scintillator Technologies
Beihang University
2023-2025
The 4D millimeter-Wave (mmWave) radar is a promising technology for vehicle sensing due to its cost-effectiveness and operability in adverse weather conditions. However, the adoption of this has been hindered by sparsity noise issues point cloud data. This article introduces spatial multi-representation fusion (SMURF), novel approach 3D object detection using single imaging radar. SMURF leverages multiple representations points, including pillarization density features multi-dimensional...
3D object detection is crucial for Autonomous Driving (AD) and Advanced Driver Assistance Systems (ADAS). However, most detectors prioritize accuracy, often overlooking network inference speed in practical applications. In this paper, we propose RadarNeXt, a real-time reliable detector based on the 4D mmWave radar point clouds. It leverages re-parameterizable neural networks to catch multi-scale features, reduce memory cost accelerate inference. Moreover, highlight irregular foreground...
As the previous state-of-the-art 4D radar-camera fusion-based 3D object detection method, LXL utilizes predicted image depth distribution maps and radar occupancy grids to assist sampling-based view transformation. However, prediction lacks accuracy consistency, concatenation-based fusion in impedes model robustness. In this work, we propose LXLv2, where modifications are made overcome limitations improve performance. Specifically, considering position error measurements, devise a...
The 4D Millimeter wave (mmWave) radar is a promising technology for vehicle sensing due to its cost-effectiveness and operability in adverse weather conditions. However, the adoption of this has been hindered by sparsity noise issues point cloud data. This paper introduces spatial multi-representation fusion (SMURF), novel approach 3D object detection using single imaging radar. SMURF leverages multiple representations points, including pillarization density features multi-dimensional...