Rakan Chabaan

Papers

Total Citations

H-Index

About

Rakan Chabaan is at the forefront of autonomous driving perception, specializing in LiDAR point cloud processing and sensor fusion. His research addresses critical challenges in how autonomous vehicles understand their environment, particularly through adaptive clustering and depth estimation techniques. His most influential work introduces an adaptive DBSCAN LiDAR point cloud clustering method (35 citations), which significantly improves object detection and recognition by dynamically adjusting clustering parameters—a fundamental advancement for real-time autonomous navigation. Building on this, Chabaan explores depth completion through guided instance segmentation fusion (8 citations), tackling the persistent problem of sparse LiDAR data by integrating semantic understanding to predict missing depth information. This work bridges the gap between raw sensor data and actionable scene understanding, enabling more robust 3D reconstruction and localization. Chabaan’s contributions are particularly notable for their practical focus on real-world autonomous driving applications, where reliable perception under varying conditions is paramount. His research continues to shape how autonomous systems interpret complex environments, making him a rising voice in the field of intelligent vehicle perception.