DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning
This addresses a gap in BEV segmentation for commercial vehicles using fisheye cameras, though it is incremental as it builds on existing LSS-based methods.
The paper tackles BEV segmentation for surround-view fisheye cameras in autonomous driving by creating a synthetic dataset and proposing a distortion-aware model with occlusion reasoning, achieving better performance without undistortion to avoid runtime and field-of-view issues.
Semantic segmentation is an effective way to perform scene understanding. Recently, segmentation in 3D Bird's Eye View (BEV) space has become popular as its directly used by drive policy. However, there is limited work on BEV segmentation for surround-view fisheye cameras, commonly used in commercial vehicles. As this task has no real-world public dataset and existing synthetic datasets do not handle amodal regions due to occlusion, we create a synthetic dataset using the Cognata simulator comprising diverse road types, weather, and lighting conditions. We generalize the BEV segmentation to work with any camera model; this is useful for mixing diverse cameras. We implement a baseline by applying cylindrical rectification on the fisheye images and using a standard LSS-based BEV segmentation model. We demonstrate that we can achieve better performance without undistortion, which has the adverse effects of increased runtime due to pre-processing, reduced field-of-view, and resampling artifacts. Further, we introduce a distortion-aware learnable BEV pooling strategy that is more effective for the fisheye cameras. We extend the model with an occlusion reasoning module, which is critical for estimating in BEV space. Qualitative performance of DaF-BEVSeg is showcased in the video at https://streamable.com/ge4v51.