CBILR: Camera Bi-directional LiDAR-Radar Fusion for Robust Perception in Autonomous Driving
Keywords: Fusion, Self-driving, Autonomous vehicle, Camera, LiDAR, Radar, Weather Conditions
Abstract: Robust perception in challenging environments is essential for safe and reliable
autonomous driving. Multi-sensor fusion, particularly camera-LiDAR-Radar inte-
gration, plays a pivotal role in achieving this goal. Different sensors have specific
advantages and disadvantages. Existing pipelines are often constrained by ad-
verse weather conditions, where cameras suffer significant degradation. This pa-
per introduces the Camera Bi-directional LiDAR-Radar (CBILR) fusion pipeline,
which leverages the strengths of sensors to enhance LiDAR and Radar point
clouds. CBILR innovates with a bi-directional prefusion step between LiDAR and
Radar, leading to richer feature representations. Prefusion combines LiDAR and
Radar points to compensate for individual sensor weaknesses. Next, the pipeline
combines all features together in the bird’s eye view (BEV) space, resulting in a
comprehensive multi-modal representation. Experiments have demonstrated that
CBILR achieves superior robustness in challenging weather scenarios.
Submission Number: 4
Loading