Xiaolong Zheng
Papers
1
Total Citations
10
H-Index
1
About
Xiaolong Zheng is a leading researcher in 3D multi-object tracking (MOT) for autonomous driving and robotics, with a particular focus on robust perception under challenging environmental conditions. His most cited work, "Cross-Modality 3D Multiobject Tracking Under Adverse Weather via Adaptive Hard Sample Mining" (2024, 10 citations), tackles the critical problem of performance degradation in MOT systems during rain, fog, or snow. Zheng’s key contribution lies in developing adaptive hard sample mining techniques that leverage cross-modal sensor fusion—combining LiDAR, radar, and camera data—to maintain tracking accuracy even when individual sensors fail. By identifying and prioritizing difficult objects (e.g., missed detections or occluded targets), his approach significantly improves robustness in real-world autonomous driving scenarios. This work has already garnered attention for addressing a major safety bottleneck in self-driving technology. Zheng’s research bridges the gap between ideal laboratory conditions and adverse real-world environments, making him a notable figure in the field of intelligent transportation systems. His ongoing efforts continue to push the boundaries of reliable 3D perception, with clear implications for safer autonomous vehicles and advanced robotics.
Research Focus
Key Achievements
Top Papers
- 1